加入实验输出（批次 13/14）
This commit is contained in:
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,524 @@
|
||||
2026-09-23 15:49:07,359 INFO Using cuda
|
||||
2026-09-23 15:49:07,360 INFO Loading text model google-bert/bert-base-uncased
|
||||
2026-09-23 15:49:10,637 INFO Loading CTC model facebook/wav2vec2-base-960h
|
||||
2026-09-23 15:49:12,766 INFO Feature models are ready on cuda
|
||||
2026-09-23 15:49:15,105 INFO [1/100] -3g5yACwYnA/13 duration=5.514s words=15 audio=535 vision=28 errors=none time=2.3s
|
||||
2026-09-23 15:49:16,768 INFO [2/100] -3g5yACwYnA/3 duration=14.389s words=29 audio=1428 vision=72 errors=none time=1.7s
|
||||
2026-09-23 15:49:18,229 INFO [3/100] -3g5yACwYnA/2 duration=9.394s words=14 audio=919 vision=47 errors=none time=1.5s
|
||||
2026-09-23 15:49:19,676 INFO [4/100] -3g5yACwYnA/9 duration=8.817s words=21 audio=865 vision=44 errors=none time=1.4s
|
||||
2026-09-23 15:49:21,012 INFO [5/100] -3nNcZdcdvU/5 duration=7.868s words=18 audio=774 vision=40 errors=none time=1.3s
|
||||
2026-09-23 15:49:25,472 INFO [6/100] -HwX2H8Z4hY/2 duration=3.982s words=8 audio=387 vision=20 errors=none time=4.5s
|
||||
2026-09-23 15:49:26,735 INFO [7/100] -HwX2H8Z4hY/5 duration=5.653s words=10 audio=550 vision=28 errors=none time=1.3s
|
||||
2026-09-23 15:49:27,899 INFO [8/100] -HwX2H8Z4hY/6 duration=3.358s words=7 audio=321 vision=17 errors=none time=1.2s
|
||||
2026-09-23 15:49:29,111 INFO [9/100] -HwX2H8Z4hY/9 duration=7.734s words=22 audio=759 vision=39 errors=none time=1.2s
|
||||
2026-09-23 15:49:30,247 INFO [10/100] -NFrJFQijFE/1 duration=5.746s words=16 audio=561 vision=29 errors=none time=1.1s
|
||||
2026-09-23 15:49:31,426 INFO [11/100] -NFrJFQijFE/2 duration=6.856s words=18 audio=665 vision=34 errors=none time=1.2s
|
||||
2026-09-23 15:49:33,035 INFO [12/100] -THoVjtIkeU/12 duration=14.896s words=39 audio=1476 vision=75 errors=none time=1.6s
|
||||
2026-09-23 15:49:34,192 INFO [13/100] -THoVjtIkeU/2 duration=4.292s words=10 audio=419 vision=22 errors=none time=1.2s
|
||||
2026-09-23 15:49:35,491 INFO [14/100] -THoVjtIkeU/6 duration=8.097s words=30 audio=794 vision=41 errors=none time=1.3s
|
||||
2026-09-23 15:49:36,799 INFO [15/100] -UuX1xuaiiE/1 duration=10.350s words=27 audio=1022 vision=52 errors=none time=1.3s
|
||||
2026-09-23 15:49:37,976 INFO [16/100] -UuX1xuaiiE/0 duration=3.633s words=9 audio=353 vision=19 errors=none time=1.2s
|
||||
2026-09-23 15:49:39,247 INFO [17/100] -UuX1xuaiiE/3 duration=4.130s words=9 audio=399 vision=21 errors=none time=1.3s
|
||||
2026-09-23 15:49:40,632 INFO [18/100] -UuX1xuaiiE/6 duration=8.114s words=22 audio=790 vision=40 errors=none time=1.4s
|
||||
2026-09-23 15:49:42,508 INFO [19/100] -a55Q6RWvTA/3 duration=22.154s words=65 audio=2204 vision=111 errors=none time=1.9s
|
||||
2026-09-23 15:49:43,810 INFO [20/100] -aNfi7CP8vM/7 duration=8.695s words=18 audio=849 vision=43 errors=none time=1.3s
|
||||
2026-09-23 15:49:45,273 INFO [21/100] -aqamKhZ1Ec/0 duration=10.967s words=14 audio=1085 vision=55 errors=none time=1.5s
|
||||
2026-09-23 15:49:46,887 INFO [22/100] -dxfTGcXJoc/1 duration=16.161s words=36 audio=1597 vision=81 errors=none time=1.6s
|
||||
2026-09-23 15:49:48,622 INFO [23/100] -dxfTGcXJoc/0 duration=20.500s words=41 audio=2037 vision=103 errors=none time=1.7s
|
||||
2026-09-23 15:49:50,293 INFO [24/100] -dxfTGcXJoc/2 duration=16.698s words=34 audio=1659 vision=84 errors=none time=1.7s
|
||||
2026-09-23 15:49:51,828 INFO [25/100] -dxfTGcXJoc/6 duration=12.735s words=27 audio=1258 vision=64 errors=none time=1.5s
|
||||
2026-09-23 15:49:53,057 INFO [26/100] -egA8-b7-3M/26 duration=6.031s words=15 audio=588 vision=30 errors=none time=1.2s
|
||||
2026-09-23 15:49:54,373 INFO [27/100] -egA8-b7-3M/17 duration=7.271s words=16 audio=705 vision=36 errors=none time=1.3s
|
||||
2026-09-23 15:49:55,696 INFO [28/100] -egA8-b7-3M/18 duration=8.386s words=22 audio=822 vision=42 errors=none time=1.3s
|
||||
2026-09-23 15:49:56,543 INFO [29/100] -egA8-b7-3M/16 duration=5.538s words=11 audio=544 vision=28 errors=none time=0.8s
|
||||
2026-09-23 15:49:57,338 INFO [30/100] -egA8-b7-3M/13 duration=4.184s words=11 audio=398 vision=21 errors=none time=0.8s
|
||||
2026-09-23 15:49:58,378 INFO [31/100] -egA8-b7-3M/1 duration=10.266s words=20 audio=1011 vision=51 errors=none time=1.0s
|
||||
2026-09-23 15:49:59,275 INFO [32/100] -egA8-b7-3M/6 duration=6.265s words=12 audio=614 vision=32 errors=none time=0.9s
|
||||
2026-09-23 15:50:00,102 INFO [33/100] -egA8-b7-3M/9 duration=5.090s words=10 audio=489 vision=25 errors=none time=0.8s
|
||||
2026-09-23 15:50:01,069 INFO [34/100] -egA8-b7-3M/20 duration=6.645s words=20 audio=643 vision=33 errors=none time=1.0s
|
||||
2026-09-23 15:50:01,864 INFO [35/100] -iRBcNs9oI8/3 duration=5.621s words=8 audio=549 vision=28 errors=none time=0.8s
|
||||
2026-09-23 15:50:02,693 INFO [36/100] -iRBcNs9oI8/7 duration=4.104s words=9 audio=396 vision=20 errors=none time=0.8s
|
||||
2026-09-23 15:50:03,453 INFO [37/100] -iRBcNs9oI8/6 duration=2.903s words=5 audio=278 vision=15 errors=none time=0.8s
|
||||
2026-09-23 15:50:04,209 INFO [38/100] -iRBcNs9oI8/9 duration=3.416s words=5 audio=333 vision=17 errors=none time=0.8s
|
||||
2026-09-23 15:50:05,067 INFO [39/100] -iRBcNs9oI8/8 duration=8.093s words=21 audio=798 vision=41 errors=none time=0.9s
|
||||
2026-09-23 15:50:06,006 INFO [40/100] -lzEya4AM_4/5 duration=7.675s words=19 audio=752 vision=39 errors=none time=0.9s
|
||||
2026-09-23 15:50:07,264 INFO [41/100] -lzEya4AM_4/6 duration=14.792s words=43 audio=1470 vision=74 errors=none time=1.3s
|
||||
2026-09-23 15:50:08,032 INFO [42/100] -mJ2ud6oKI8/1 duration=6.103s words=13 audio=601 vision=31 errors=none time=0.8s
|
||||
2026-09-23 15:50:08,850 INFO [43/100] -mJ2ud6oKI8/2 duration=5.731s words=11 audio=566 vision=29 errors=none time=0.8s
|
||||
2026-09-23 15:50:09,622 INFO [44/100] -mJ2ud6oKI8/6 duration=2.257s words=5 audio=218 vision=12 errors=none time=0.8s
|
||||
2026-09-23 15:50:10,606 INFO [45/100] -mJ2ud6oKI8/9 duration=7.033s words=22 audio=686 vision=35 errors=none time=1.0s
|
||||
2026-09-23 15:50:11,466 INFO [46/100] -mJ2ud6oKI8/8 duration=4.192s words=11 audio=413 vision=21 errors=none time=0.9s
|
||||
2026-09-23 15:50:12,394 INFO [47/100] -mqbVkbCndg/0 duration=6.467s words=12 audio=634 vision=33 errors=none time=0.9s
|
||||
2026-09-23 15:50:13,234 INFO [48/100] -t217m2on-s/2 duration=5.686s words=12 audio=559 vision=29 errors=none time=0.8s
|
||||
2026-09-23 15:50:14,758 INFO [49/100] -t217m2on-s/7 duration=17.183s words=45 audio=1698 vision=86 errors=none time=1.5s
|
||||
2026-09-23 15:50:15,706 INFO [50/100] -tANM6ETl_M/3 duration=6.758s words=22 audio=656 vision=34 errors=none time=0.9s
|
||||
2026-09-23 15:50:16,551 INFO [51/100] -tPCytz4rww/11 duration=5.467s words=17 audio=533 vision=28 errors=none time=0.8s
|
||||
2026-09-23 15:50:17,370 INFO [52/100] -tPCytz4rww/10 duration=4.789s words=12 audio=463 vision=24 errors=none time=0.8s
|
||||
2026-09-23 15:50:18,472 INFO [53/100] -tPCytz4rww/12 duration=11.864s words=26 audio=1169 vision=59 errors=none time=1.1s
|
||||
2026-09-23 15:50:19,381 INFO [54/100] -tPCytz4rww/16 duration=7.206s words=16 audio=709 vision=36 errors=none time=0.9s
|
||||
2026-09-23 15:50:20,275 INFO [55/100] -tPCytz4rww/18 duration=6.645s words=16 audio=652 vision=34 errors=none time=0.9s
|
||||
2026-09-23 15:50:21,266 INFO [56/100] -vxjVxOeScU/4 duration=9.127s words=21 audio=899 vision=46 errors=none time=1.0s
|
||||
2026-09-23 15:50:22,124 INFO [57/100] -wMB_hJL-3o/7 duration=6.044s words=22 audio=593 vision=31 errors=none time=0.9s
|
||||
2026-09-23 15:50:23,051 INFO [58/100] -wny0OAz3g8/1 duration=6.844s words=23 audio=673 vision=35 errors=none time=0.9s
|
||||
2026-09-23 15:50:23,830 INFO [59/100] -wny0OAz3g8/0 duration=3.333s words=9 audio=323 vision=17 errors=none time=0.8s
|
||||
2026-09-23 15:50:24,744 INFO [60/100] -wny0OAz3g8/3 duration=6.146s words=20 audio=605 vision=31 errors=none time=0.9s
|
||||
2026-09-23 15:50:25,710 INFO [61/100] -wny0OAz3g8/2 duration=6.687s words=23 audio=648 vision=33 errors=none time=1.0s
|
||||
2026-09-23 15:50:26,635 INFO [62/100] -wny0OAz3g8/5 duration=6.912s words=20 audio=670 vision=34 errors=none time=0.9s
|
||||
2026-09-23 15:50:27,696 INFO [63/100] -wny0OAz3g8/7 duration=8.068s words=29 audio=787 vision=40 errors=none time=1.1s
|
||||
2026-09-23 15:50:28,637 INFO [64/100] -wny0OAz3g8/9 duration=6.213s words=20 audio=600 vision=31 errors=none time=0.9s
|
||||
2026-09-23 15:50:29,458 INFO [65/100] -571d8cVauQ/0 duration=5.067s words=12 audio=495 vision=26 errors=none time=0.8s
|
||||
2026-09-23 15:50:30,700 INFO [66/100] -571d8cVauQ/5 duration=15.273s words=43 audio=1507 vision=76 errors=none time=1.2s
|
||||
2026-09-23 15:50:31,668 INFO [67/100] -I_e4mIh0yE/1 duration=7.622s words=18 audio=740 vision=38 errors=none time=1.0s
|
||||
2026-09-23 15:50:32,696 INFO [68/100] -I_e4mIh0yE/3 duration=9.163s words=22 audio=895 vision=46 errors=none time=1.0s
|
||||
2026-09-23 15:50:33,676 INFO [69/100] -UacrmKiTn4/10 duration=7.362s words=18 audio=720 vision=37 errors=none time=1.0s
|
||||
2026-09-23 15:50:34,598 INFO [70/100] -UacrmKiTn4/4 duration=4.741s words=14 audio=464 vision=24 errors=none time=0.9s
|
||||
2026-09-23 15:50:35,490 INFO [71/100] -hnBHBN8p5A/7 duration=7.372s words=13 audio=726 vision=36 errors=none time=0.9s
|
||||
2026-09-23 15:50:36,366 INFO [72/100] -hnBHBN8p5A/6 duration=6.401s words=13 audio=629 vision=31 errors=none time=0.9s
|
||||
2026-09-23 15:50:37,221 INFO [73/100] -qDkUB0GgYY/6 duration=4.678s words=16 audio=457 vision=24 errors=none time=0.9s
|
||||
2026-09-23 15:50:38,259 INFO [74/100] -uywlfIYOS8/4 duration=6.045s words=18 audio=584 vision=30 errors=none time=1.0s
|
||||
2026-09-23 15:50:39,444 INFO [75/100] -6rXp3zJ3kc/8 duration=12.805s words=34 audio=1269 vision=64 errors=none time=1.2s
|
||||
2026-09-23 15:50:40,445 INFO [76/100] -9y-fZ3swSY/0 duration=6.833s words=22 audio=671 vision=35 errors=none time=1.0s
|
||||
2026-09-23 15:50:41,357 INFO [77/100] -9y-fZ3swSY/4 duration=2.821s words=9 audio=262 vision=14 errors=none time=0.9s
|
||||
2026-09-23 15:50:42,285 INFO [78/100] -9y-fZ3swSY/8 duration=4.989s words=12 audio=487 vision=25 errors=none time=0.9s
|
||||
2026-09-23 15:50:44,049 INFO [79/100] -AUZQgSxyPQ/2 duration=22.511s words=41 audio=2236 vision=113 errors=none time=1.8s
|
||||
2026-09-23 15:50:45,069 INFO [80/100] -HeZS2-Prhc/2 duration=8.262s words=16 audio=811 vision=41 errors=none time=1.0s
|
||||
2026-09-23 15:50:46,114 INFO [81/100] -MeTTeMJBNc/0 duration=9.300s words=21 audio=917 vision=47 errors=none time=1.0s
|
||||
2026-09-23 15:50:46,995 INFO [82/100] -MeTTeMJBNc/13 duration=5.430s words=14 audio=521 vision=27 errors=none time=0.9s
|
||||
2026-09-23 15:50:48,194 INFO [83/100] -MeTTeMJBNc/7 duration=10.517s words=31 audio=1037 vision=53 errors=none time=1.2s
|
||||
2026-09-23 15:50:49,142 INFO [84/100] -RfYyzHpjk4/11 duration=5.239s words=17 audio=503 vision=26 errors=none time=0.9s
|
||||
2026-09-23 15:50:50,076 INFO [85/100] -RfYyzHpjk4/8 duration=4.589s words=17 audio=449 vision=23 errors=none time=0.9s
|
||||
2026-09-23 15:50:51,024 INFO [86/100] -RfYyzHpjk4/2 duration=5.516s words=25 audio=535 vision=28 errors=none time=0.9s
|
||||
2026-09-23 15:50:52,002 INFO [87/100] -UUCSKoHeMA/0 duration=7.800s words=18 audio=769 vision=39 errors=none time=1.0s
|
||||
2026-09-23 15:50:52,832 INFO [88/100] -ri04Z7vwnc/0 duration=2.807s words=8 audio=272 vision=14 errors=none time=0.8s
|
||||
2026-09-23 15:50:53,641 INFO [89/100] -ri04Z7vwnc/2 duration=6.027s words=16 audio=587 vision=29 errors=none time=0.8s
|
||||
2026-09-23 15:50:55,466 INFO [90/100] -ri04Z7vwnc/5 duration=3.545s words=9 audio=339 vision=17 errors=none time=1.8s
|
||||
2026-09-23 15:50:56,397 INFO [91/100] -s9qJ7ATP7w/1 duration=4.792s words=11 audio=460 vision=24 errors=none time=0.9s
|
||||
2026-09-23 15:50:57,394 INFO [92/100] -s9qJ7ATP7w/0 duration=6.800s words=24 audio=667 vision=34 errors=none time=1.0s
|
||||
2026-09-23 15:50:58,500 INFO [93/100] -s9qJ7ATP7w/5 duration=8.561s words=19 audio=835 vision=43 errors=none time=1.1s
|
||||
2026-09-23 15:50:59,465 INFO [94/100] -s9qJ7ATP7w/4 duration=4.427s words=9 audio=420 vision=22 errors=none time=1.0s
|
||||
2026-09-23 15:51:00,463 INFO [95/100] -s9qJ7ATP7w/7 duration=6.966s words=28 audio=679 vision=35 errors=none time=1.0s
|
||||
2026-09-23 15:51:01,221 INFO [96/100] -s9qJ7ATP7w/6 duration=2.475s words=5 audio=227 vision=12 errors=none time=0.8s
|
||||
2026-09-23 15:51:02,021 INFO [97/100] -s9qJ7ATP7w/8 duration=3.295s words=13 audio=314 vision=17 errors=none time=0.8s
|
||||
2026-09-23 15:51:04,111 INFO [98/100] -yRb-Jum7EQ/1 duration=29.288s words=49 audio=2906 vision=146 errors=none time=2.1s
|
||||
2026-09-23 15:51:05,419 INFO [99/100] -yRb-Jum7EQ/5 duration=13.169s words=25 audio=1300 vision=66 errors=none time=1.3s
|
||||
2026-09-23 15:51:06,588 INFO [100/100] -yRb-Jum7EQ/6 duration=11.242s words=19 audio=1120 vision=56 errors=none time=1.2s
|
||||
2026-09-23 16:01:22,907 INFO Using cuda
|
||||
2026-09-23 16:01:22,908 INFO Loading text model google-bert/bert-base-uncased
|
||||
2026-09-23 16:01:26,096 INFO Loading CTC model facebook/wav2vec2-base-960h
|
||||
2026-09-23 16:01:28,550 INFO Loading general vision model facebook/deit-tiny-patch16-224
|
||||
2026-09-23 16:01:31,258 INFO Feature models are ready on cuda
|
||||
2026-09-23 16:01:34,860 INFO [1/100] -3g5yACwYnA/13 duration=5.514s words=15 audio=535 vision=28 errors=none time=3.6s
|
||||
2026-09-23 16:01:36,835 INFO [2/100] -3g5yACwYnA/3 duration=14.389s words=29 audio=1428 vision=72 errors=none time=2.0s
|
||||
2026-09-23 16:01:38,402 INFO [3/100] -3g5yACwYnA/2 duration=9.394s words=14 audio=919 vision=47 errors=none time=1.6s
|
||||
2026-09-23 16:01:40,067 INFO [4/100] -3g5yACwYnA/9 duration=8.817s words=21 audio=865 vision=44 errors=none time=1.7s
|
||||
2026-09-23 16:01:41,458 INFO [5/100] -3nNcZdcdvU/5 duration=7.868s words=18 audio=774 vision=40 errors=none time=1.4s
|
||||
2026-09-23 16:01:43,914 INFO [6/100] -HwX2H8Z4hY/2 duration=3.982s words=8 audio=387 vision=20 errors=none time=2.5s
|
||||
2026-09-23 16:01:45,274 INFO [7/100] -HwX2H8Z4hY/5 duration=5.653s words=10 audio=550 vision=28 errors=none time=1.4s
|
||||
2026-09-23 16:01:46,554 INFO [8/100] -HwX2H8Z4hY/6 duration=3.358s words=7 audio=321 vision=17 errors=none time=1.3s
|
||||
2026-09-23 16:01:47,964 INFO [9/100] -HwX2H8Z4hY/9 duration=7.734s words=22 audio=759 vision=39 errors=none time=1.4s
|
||||
2026-09-23 16:01:49,239 INFO [10/100] -NFrJFQijFE/1 duration=5.746s words=16 audio=561 vision=29 errors=none time=1.3s
|
||||
2026-09-23 16:01:50,533 INFO [11/100] -NFrJFQijFE/2 duration=6.856s words=18 audio=665 vision=34 errors=none time=1.3s
|
||||
2026-09-23 16:01:52,296 INFO [12/100] -THoVjtIkeU/12 duration=14.896s words=39 audio=1476 vision=75 errors=none time=1.8s
|
||||
2026-09-23 16:01:53,508 INFO [13/100] -THoVjtIkeU/2 duration=4.292s words=10 audio=419 vision=22 errors=none time=1.2s
|
||||
2026-09-23 16:01:54,923 INFO [14/100] -THoVjtIkeU/6 duration=8.097s words=30 audio=794 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:01:56,509 INFO [15/100] -UuX1xuaiiE/1 duration=10.350s words=27 audio=1022 vision=52 errors=none time=1.6s
|
||||
2026-09-23 16:01:57,780 INFO [16/100] -UuX1xuaiiE/0 duration=3.633s words=9 audio=353 vision=19 errors=none time=1.3s
|
||||
2026-09-23 16:01:59,150 INFO [17/100] -UuX1xuaiiE/3 duration=4.130s words=9 audio=399 vision=21 errors=none time=1.4s
|
||||
2026-09-23 16:02:00,779 INFO [18/100] -UuX1xuaiiE/6 duration=8.114s words=22 audio=790 vision=40 errors=none time=1.6s
|
||||
2026-09-23 16:02:02,801 INFO [19/100] -a55Q6RWvTA/3 duration=22.154s words=65 audio=2204 vision=111 errors=none time=2.0s
|
||||
2026-09-23 16:02:04,221 INFO [20/100] -aNfi7CP8vM/7 duration=8.695s words=18 audio=849 vision=43 errors=none time=1.4s
|
||||
2026-09-23 16:02:05,945 INFO [21/100] -aqamKhZ1Ec/0 duration=10.967s words=14 audio=1085 vision=55 errors=none time=1.7s
|
||||
2026-09-23 16:02:07,796 INFO [22/100] -dxfTGcXJoc/1 duration=16.161s words=36 audio=1597 vision=81 errors=none time=1.9s
|
||||
2026-09-23 16:02:09,661 INFO [23/100] -dxfTGcXJoc/0 duration=20.500s words=41 audio=2037 vision=103 errors=none time=1.9s
|
||||
2026-09-23 16:02:11,373 INFO [24/100] -dxfTGcXJoc/2 duration=16.698s words=34 audio=1659 vision=84 errors=none time=1.7s
|
||||
2026-09-23 16:02:12,945 INFO [25/100] -dxfTGcXJoc/6 duration=12.735s words=27 audio=1258 vision=64 errors=none time=1.6s
|
||||
2026-09-23 16:02:14,241 INFO [26/100] -egA8-b7-3M/26 duration=6.031s words=15 audio=588 vision=30 errors=none time=1.3s
|
||||
2026-09-23 16:02:15,532 INFO [27/100] -egA8-b7-3M/17 duration=7.271s words=16 audio=705 vision=36 errors=none time=1.3s
|
||||
2026-09-23 16:02:16,904 INFO [28/100] -egA8-b7-3M/18 duration=8.386s words=22 audio=822 vision=42 errors=none time=1.4s
|
||||
2026-09-23 16:02:18,214 INFO [29/100] -egA8-b7-3M/16 duration=5.538s words=11 audio=544 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:02:19,366 INFO [30/100] -egA8-b7-3M/13 duration=4.184s words=11 audio=398 vision=21 errors=none time=1.2s
|
||||
2026-09-23 16:02:20,920 INFO [31/100] -egA8-b7-3M/1 duration=10.266s words=20 audio=1011 vision=51 errors=none time=1.6s
|
||||
2026-09-23 16:02:22,209 INFO [32/100] -egA8-b7-3M/6 duration=6.265s words=12 audio=614 vision=32 errors=none time=1.3s
|
||||
2026-09-23 16:02:23,448 INFO [33/100] -egA8-b7-3M/9 duration=5.090s words=10 audio=489 vision=25 errors=none time=1.2s
|
||||
2026-09-23 16:02:24,776 INFO [34/100] -egA8-b7-3M/20 duration=6.645s words=20 audio=643 vision=33 errors=none time=1.3s
|
||||
2026-09-23 16:02:26,054 INFO [35/100] -iRBcNs9oI8/3 duration=5.621s words=8 audio=549 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:02:27,321 INFO [36/100] -iRBcNs9oI8/7 duration=4.104s words=9 audio=396 vision=20 errors=none time=1.3s
|
||||
2026-09-23 16:02:28,518 INFO [37/100] -iRBcNs9oI8/6 duration=2.903s words=5 audio=278 vision=15 errors=none time=1.2s
|
||||
2026-09-23 16:02:29,678 INFO [38/100] -iRBcNs9oI8/9 duration=3.416s words=5 audio=333 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:02:31,077 INFO [39/100] -iRBcNs9oI8/8 duration=8.093s words=21 audio=798 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:02:32,367 INFO [40/100] -lzEya4AM_4/5 duration=7.675s words=19 audio=752 vision=39 errors=none time=1.3s
|
||||
2026-09-23 16:02:34,086 INFO [41/100] -lzEya4AM_4/6 duration=14.792s words=43 audio=1470 vision=74 errors=none time=1.7s
|
||||
2026-09-23 16:02:35,377 INFO [42/100] -mJ2ud6oKI8/1 duration=6.103s words=13 audio=601 vision=31 errors=none time=1.3s
|
||||
2026-09-23 16:02:36,617 INFO [43/100] -mJ2ud6oKI8/2 duration=5.731s words=11 audio=566 vision=29 errors=none time=1.2s
|
||||
2026-09-23 16:02:37,814 INFO [44/100] -mJ2ud6oKI8/6 duration=2.257s words=5 audio=218 vision=12 errors=none time=1.2s
|
||||
2026-09-23 16:02:39,288 INFO [45/100] -mJ2ud6oKI8/9 duration=7.033s words=22 audio=686 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:02:40,692 INFO [46/100] -mJ2ud6oKI8/8 duration=4.192s words=11 audio=413 vision=21 errors=none time=1.4s
|
||||
2026-09-23 16:02:42,285 INFO [47/100] -mqbVkbCndg/0 duration=6.467s words=12 audio=634 vision=33 errors=none time=1.6s
|
||||
2026-09-23 16:02:43,571 INFO [48/100] -t217m2on-s/2 duration=5.686s words=12 audio=559 vision=29 errors=none time=1.3s
|
||||
2026-09-23 16:02:45,390 INFO [49/100] -t217m2on-s/7 duration=17.183s words=45 audio=1698 vision=86 errors=none time=1.8s
|
||||
2026-09-23 16:02:46,908 INFO [50/100] -tANM6ETl_M/3 duration=6.758s words=22 audio=656 vision=34 errors=none time=1.5s
|
||||
2026-09-23 16:02:48,218 INFO [51/100] -tPCytz4rww/11 duration=5.467s words=17 audio=533 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:02:49,464 INFO [52/100] -tPCytz4rww/10 duration=4.789s words=12 audio=463 vision=24 errors=none time=1.2s
|
||||
2026-09-23 16:02:51,060 INFO [53/100] -tPCytz4rww/12 duration=11.864s words=26 audio=1169 vision=59 errors=none time=1.6s
|
||||
2026-09-23 16:02:52,398 INFO [54/100] -tPCytz4rww/16 duration=7.206s words=16 audio=709 vision=36 errors=none time=1.3s
|
||||
2026-09-23 16:02:53,706 INFO [55/100] -tPCytz4rww/18 duration=6.645s words=16 audio=652 vision=34 errors=none time=1.3s
|
||||
2026-09-23 16:02:55,162 INFO [56/100] -vxjVxOeScU/4 duration=9.127s words=21 audio=899 vision=46 errors=none time=1.5s
|
||||
2026-09-23 16:02:56,407 INFO [57/100] -wMB_hJL-3o/7 duration=6.044s words=22 audio=593 vision=31 errors=none time=1.2s
|
||||
2026-09-23 16:02:57,895 INFO [58/100] -wny0OAz3g8/1 duration=6.844s words=23 audio=673 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:02:59,118 INFO [59/100] -wny0OAz3g8/0 duration=3.333s words=9 audio=323 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:03:00,510 INFO [60/100] -wny0OAz3g8/3 duration=6.146s words=20 audio=605 vision=31 errors=none time=1.4s
|
||||
2026-09-23 16:03:02,006 INFO [61/100] -wny0OAz3g8/2 duration=6.687s words=23 audio=648 vision=33 errors=none time=1.5s
|
||||
2026-09-23 16:03:03,431 INFO [62/100] -wny0OAz3g8/5 duration=6.912s words=20 audio=670 vision=34 errors=none time=1.4s
|
||||
2026-09-23 16:03:04,905 INFO [63/100] -wny0OAz3g8/7 duration=8.068s words=29 audio=787 vision=40 errors=none time=1.5s
|
||||
2026-09-23 16:03:06,321 INFO [64/100] -wny0OAz3g8/9 duration=6.213s words=20 audio=600 vision=31 errors=none time=1.4s
|
||||
2026-09-23 16:03:07,543 INFO [65/100] -571d8cVauQ/0 duration=5.067s words=12 audio=495 vision=26 errors=none time=1.2s
|
||||
2026-09-23 16:03:09,302 INFO [66/100] -571d8cVauQ/5 duration=15.273s words=43 audio=1507 vision=76 errors=none time=1.8s
|
||||
2026-09-23 16:03:10,771 INFO [67/100] -I_e4mIh0yE/1 duration=7.622s words=18 audio=740 vision=38 errors=none time=1.5s
|
||||
2026-09-23 16:03:12,211 INFO [68/100] -I_e4mIh0yE/3 duration=9.163s words=22 audio=895 vision=46 errors=none time=1.4s
|
||||
2026-09-23 16:03:13,574 INFO [69/100] -UacrmKiTn4/10 duration=7.362s words=18 audio=720 vision=37 errors=none time=1.4s
|
||||
2026-09-23 16:03:14,775 INFO [70/100] -UacrmKiTn4/4 duration=4.741s words=14 audio=464 vision=24 errors=none time=1.2s
|
||||
2026-09-23 16:03:16,151 INFO [71/100] -hnBHBN8p5A/7 duration=7.372s words=13 audio=726 vision=36 errors=none time=1.4s
|
||||
2026-09-23 16:03:17,533 INFO [72/100] -hnBHBN8p5A/6 duration=6.401s words=13 audio=629 vision=31 errors=none time=1.4s
|
||||
2026-09-23 16:03:18,749 INFO [73/100] -qDkUB0GgYY/6 duration=4.678s words=16 audio=457 vision=24 errors=none time=1.2s
|
||||
2026-09-23 16:03:20,083 INFO [74/100] -uywlfIYOS8/4 duration=6.045s words=18 audio=584 vision=30 errors=none time=1.3s
|
||||
2026-09-23 16:03:21,711 INFO [75/100] -6rXp3zJ3kc/8 duration=12.805s words=34 audio=1269 vision=64 errors=none time=1.6s
|
||||
2026-09-23 16:03:23,249 INFO [76/100] -9y-fZ3swSY/0 duration=6.833s words=22 audio=671 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:03:24,541 INFO [77/100] -9y-fZ3swSY/4 duration=2.821s words=9 audio=262 vision=14 errors=none time=1.3s
|
||||
2026-09-23 16:03:25,926 INFO [78/100] -9y-fZ3swSY/8 duration=4.989s words=12 audio=487 vision=25 errors=none time=1.4s
|
||||
2026-09-23 16:03:28,421 INFO [79/100] -AUZQgSxyPQ/2 duration=22.511s words=41 audio=2236 vision=113 errors=none time=2.5s
|
||||
2026-09-23 16:03:29,827 INFO [80/100] -HeZS2-Prhc/2 duration=8.262s words=16 audio=811 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:03:31,296 INFO [81/100] -MeTTeMJBNc/0 duration=9.300s words=21 audio=917 vision=47 errors=none time=1.5s
|
||||
2026-09-23 16:03:32,485 INFO [82/100] -MeTTeMJBNc/13 duration=5.430s words=14 audio=521 vision=27 errors=none time=1.2s
|
||||
2026-09-23 16:03:34,001 INFO [83/100] -MeTTeMJBNc/7 duration=10.517s words=31 audio=1037 vision=53 errors=none time=1.5s
|
||||
2026-09-23 16:03:35,428 INFO [84/100] -RfYyzHpjk4/11 duration=5.239s words=17 audio=503 vision=26 errors=none time=1.4s
|
||||
2026-09-23 16:03:36,824 INFO [85/100] -RfYyzHpjk4/8 duration=4.589s words=17 audio=449 vision=23 errors=none time=1.4s
|
||||
2026-09-23 16:03:38,166 INFO [86/100] -RfYyzHpjk4/2 duration=5.516s words=25 audio=535 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:03:39,559 INFO [87/100] -UUCSKoHeMA/0 duration=7.800s words=18 audio=769 vision=39 errors=none time=1.4s
|
||||
2026-09-23 16:03:40,837 INFO [88/100] -ri04Z7vwnc/0 duration=2.807s words=8 audio=272 vision=14 errors=none time=1.3s
|
||||
2026-09-23 16:03:42,133 INFO [89/100] -ri04Z7vwnc/2 duration=6.027s words=16 audio=587 vision=29 errors=none time=1.3s
|
||||
2026-09-23 16:03:43,436 INFO [90/100] -ri04Z7vwnc/5 duration=3.545s words=9 audio=339 vision=17 errors=none time=1.3s
|
||||
2026-09-23 16:03:44,772 INFO [91/100] -s9qJ7ATP7w/1 duration=4.792s words=11 audio=460 vision=24 errors=none time=1.3s
|
||||
2026-09-23 16:03:46,192 INFO [92/100] -s9qJ7ATP7w/0 duration=6.800s words=24 audio=667 vision=34 errors=none time=1.4s
|
||||
2026-09-23 16:03:47,807 INFO [93/100] -s9qJ7ATP7w/5 duration=8.561s words=19 audio=835 vision=43 errors=none time=1.6s
|
||||
2026-09-23 16:03:49,192 INFO [94/100] -s9qJ7ATP7w/4 duration=4.427s words=9 audio=420 vision=22 errors=none time=1.4s
|
||||
2026-09-23 16:03:50,645 INFO [95/100] -s9qJ7ATP7w/7 duration=6.966s words=28 audio=679 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:03:51,818 INFO [96/100] -s9qJ7ATP7w/6 duration=2.475s words=5 audio=227 vision=12 errors=none time=1.2s
|
||||
2026-09-23 16:03:53,068 INFO [97/100] -s9qJ7ATP7w/8 duration=3.295s words=13 audio=314 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:03:56,076 INFO [98/100] -yRb-Jum7EQ/1 duration=29.288s words=49 audio=2906 vision=146 errors=none time=3.0s
|
||||
2026-09-23 16:03:57,818 INFO [99/100] -yRb-Jum7EQ/5 duration=13.169s words=25 audio=1300 vision=66 errors=none time=1.7s
|
||||
2026-09-23 16:03:59,499 INFO [100/100] -yRb-Jum7EQ/6 duration=11.242s words=19 audio=1120 vision=56 errors=none time=1.7s
|
||||
2026-09-23 16:06:33,215 INFO Using cuda
|
||||
2026-09-23 16:06:33,215 INFO Loading text model google-bert/bert-base-uncased
|
||||
2026-09-23 16:06:35,984 INFO Loading CTC model facebook/wav2vec2-base-960h
|
||||
2026-09-23 16:06:38,108 INFO Loading general vision model facebook/deit-tiny-patch16-224
|
||||
2026-09-23 16:06:40,783 INFO Feature models are ready on cuda
|
||||
2026-09-23 16:06:43,273 INFO [1/100] -3g5yACwYnA/13 duration=5.514s words=15 audio=535 vision=28 errors=none time=2.5s
|
||||
2026-09-23 16:06:45,250 INFO [2/100] -3g5yACwYnA/3 duration=14.389s words=29 audio=1428 vision=72 errors=none time=2.0s
|
||||
2026-09-23 16:06:46,779 INFO [3/100] -3g5yACwYnA/2 duration=9.394s words=14 audio=919 vision=47 errors=none time=1.5s
|
||||
2026-09-23 16:06:48,339 INFO [4/100] -3g5yACwYnA/9 duration=8.817s words=21 audio=865 vision=44 errors=none time=1.6s
|
||||
2026-09-23 16:06:49,659 INFO [5/100] -3nNcZdcdvU/5 duration=7.868s words=18 audio=774 vision=40 errors=none time=1.3s
|
||||
2026-09-23 16:06:50,930 INFO [6/100] -HwX2H8Z4hY/2 duration=3.982s words=8 audio=387 vision=20 errors=none time=1.3s
|
||||
2026-09-23 16:06:52,335 INFO [7/100] -HwX2H8Z4hY/5 duration=5.653s words=10 audio=550 vision=28 errors=none time=1.4s
|
||||
2026-09-23 16:06:53,617 INFO [8/100] -HwX2H8Z4hY/6 duration=3.358s words=7 audio=321 vision=17 errors=none time=1.3s
|
||||
2026-09-23 16:06:55,019 INFO [9/100] -HwX2H8Z4hY/9 duration=7.734s words=22 audio=759 vision=39 errors=none time=1.4s
|
||||
2026-09-23 16:06:56,254 INFO [10/100] -NFrJFQijFE/1 duration=5.746s words=16 audio=561 vision=29 errors=none time=1.2s
|
||||
2026-09-23 16:06:57,570 INFO [11/100] -NFrJFQijFE/2 duration=6.856s words=18 audio=665 vision=34 errors=none time=1.3s
|
||||
2026-09-23 16:06:59,246 INFO [12/100] -THoVjtIkeU/12 duration=14.896s words=39 audio=1476 vision=75 errors=none time=1.7s
|
||||
2026-09-23 16:07:00,466 INFO [13/100] -THoVjtIkeU/2 duration=4.292s words=10 audio=419 vision=22 errors=none time=1.2s
|
||||
2026-09-23 16:07:01,842 INFO [14/100] -THoVjtIkeU/6 duration=8.097s words=30 audio=794 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:07:03,446 INFO [15/100] -UuX1xuaiiE/1 duration=10.350s words=27 audio=1022 vision=52 errors=none time=1.6s
|
||||
2026-09-23 16:07:04,623 INFO [16/100] -UuX1xuaiiE/0 duration=3.633s words=9 audio=353 vision=19 errors=none time=1.2s
|
||||
2026-09-23 16:07:05,959 INFO [17/100] -UuX1xuaiiE/3 duration=4.130s words=9 audio=399 vision=21 errors=none time=1.3s
|
||||
2026-09-23 16:07:07,681 INFO [18/100] -UuX1xuaiiE/6 duration=8.114s words=22 audio=790 vision=40 errors=none time=1.7s
|
||||
2026-09-23 16:07:09,746 INFO [19/100] -a55Q6RWvTA/3 duration=22.154s words=65 audio=2204 vision=111 errors=none time=2.1s
|
||||
2026-09-23 16:07:11,117 INFO [20/100] -aNfi7CP8vM/7 duration=8.695s words=18 audio=849 vision=43 errors=none time=1.4s
|
||||
2026-09-23 16:07:12,857 INFO [21/100] -aqamKhZ1Ec/0 duration=10.967s words=14 audio=1085 vision=55 errors=none time=1.7s
|
||||
2026-09-23 16:07:14,635 INFO [22/100] -dxfTGcXJoc/1 duration=16.161s words=36 audio=1597 vision=81 errors=none time=1.8s
|
||||
2026-09-23 16:07:16,450 INFO [23/100] -dxfTGcXJoc/0 duration=20.500s words=41 audio=2037 vision=103 errors=none time=1.8s
|
||||
2026-09-23 16:07:18,194 INFO [24/100] -dxfTGcXJoc/2 duration=16.698s words=34 audio=1659 vision=84 errors=none time=1.7s
|
||||
2026-09-23 16:07:19,704 INFO [25/100] -dxfTGcXJoc/6 duration=12.735s words=27 audio=1258 vision=64 errors=none time=1.5s
|
||||
2026-09-23 16:07:20,975 INFO [26/100] -egA8-b7-3M/26 duration=6.031s words=15 audio=588 vision=30 errors=none time=1.3s
|
||||
2026-09-23 16:07:22,288 INFO [27/100] -egA8-b7-3M/17 duration=7.271s words=16 audio=705 vision=36 errors=none time=1.3s
|
||||
2026-09-23 16:07:23,661 INFO [28/100] -egA8-b7-3M/18 duration=8.386s words=22 audio=822 vision=42 errors=none time=1.4s
|
||||
2026-09-23 16:07:24,867 INFO [29/100] -egA8-b7-3M/16 duration=5.538s words=11 audio=544 vision=28 errors=none time=1.2s
|
||||
2026-09-23 16:07:26,031 INFO [30/100] -egA8-b7-3M/13 duration=4.184s words=11 audio=398 vision=21 errors=none time=1.2s
|
||||
2026-09-23 16:07:27,479 INFO [31/100] -egA8-b7-3M/1 duration=10.266s words=20 audio=1011 vision=51 errors=none time=1.4s
|
||||
2026-09-23 16:07:28,753 INFO [32/100] -egA8-b7-3M/6 duration=6.265s words=12 audio=614 vision=32 errors=none time=1.3s
|
||||
2026-09-23 16:07:29,993 INFO [33/100] -egA8-b7-3M/9 duration=5.090s words=10 audio=489 vision=25 errors=none time=1.2s
|
||||
2026-09-23 16:07:31,296 INFO [34/100] -egA8-b7-3M/20 duration=6.645s words=20 audio=643 vision=33 errors=none time=1.3s
|
||||
2026-09-23 16:07:32,560 INFO [35/100] -iRBcNs9oI8/3 duration=5.621s words=8 audio=549 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:07:33,725 INFO [36/100] -iRBcNs9oI8/7 duration=4.104s words=9 audio=396 vision=20 errors=none time=1.2s
|
||||
2026-09-23 16:07:34,863 INFO [37/100] -iRBcNs9oI8/6 duration=2.903s words=5 audio=278 vision=15 errors=none time=1.1s
|
||||
2026-09-23 16:07:36,086 INFO [38/100] -iRBcNs9oI8/9 duration=3.416s words=5 audio=333 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:07:37,454 INFO [39/100] -iRBcNs9oI8/8 duration=8.093s words=21 audio=798 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:07:38,794 INFO [40/100] -lzEya4AM_4/5 duration=7.675s words=19 audio=752 vision=39 errors=none time=1.3s
|
||||
2026-09-23 16:07:40,508 INFO [41/100] -lzEya4AM_4/6 duration=14.792s words=43 audio=1470 vision=74 errors=none time=1.7s
|
||||
2026-09-23 16:07:41,769 INFO [42/100] -mJ2ud6oKI8/1 duration=6.103s words=13 audio=601 vision=31 errors=none time=1.3s
|
||||
2026-09-23 16:07:43,141 INFO [43/100] -mJ2ud6oKI8/2 duration=5.731s words=11 audio=566 vision=29 errors=none time=1.4s
|
||||
2026-09-23 16:07:44,318 INFO [44/100] -mJ2ud6oKI8/6 duration=2.257s words=5 audio=218 vision=12 errors=none time=1.2s
|
||||
2026-09-23 16:07:45,801 INFO [45/100] -mJ2ud6oKI8/9 duration=7.033s words=22 audio=686 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:07:47,128 INFO [46/100] -mJ2ud6oKI8/8 duration=4.192s words=11 audio=413 vision=21 errors=none time=1.3s
|
||||
2026-09-23 16:07:48,509 INFO [47/100] -mqbVkbCndg/0 duration=6.467s words=12 audio=634 vision=33 errors=none time=1.4s
|
||||
2026-09-23 16:07:49,698 INFO [48/100] -t217m2on-s/2 duration=5.686s words=12 audio=559 vision=29 errors=none time=1.2s
|
||||
2026-09-23 16:07:51,459 INFO [49/100] -t217m2on-s/7 duration=17.183s words=45 audio=1698 vision=86 errors=none time=1.8s
|
||||
2026-09-23 16:07:52,861 INFO [50/100] -tANM6ETl_M/3 duration=6.758s words=22 audio=656 vision=34 errors=none time=1.4s
|
||||
2026-09-23 16:07:54,073 INFO [51/100] -tPCytz4rww/11 duration=5.467s words=17 audio=533 vision=28 errors=none time=1.2s
|
||||
2026-09-23 16:07:55,326 INFO [52/100] -tPCytz4rww/10 duration=4.789s words=12 audio=463 vision=24 errors=none time=1.3s
|
||||
2026-09-23 16:07:56,855 INFO [53/100] -tPCytz4rww/12 duration=11.864s words=26 audio=1169 vision=59 errors=none time=1.5s
|
||||
2026-09-23 16:07:58,162 INFO [54/100] -tPCytz4rww/16 duration=7.206s words=16 audio=709 vision=36 errors=none time=1.3s
|
||||
2026-09-23 16:07:59,456 INFO [55/100] -tPCytz4rww/18 duration=6.645s words=16 audio=652 vision=34 errors=none time=1.3s
|
||||
2026-09-23 16:08:00,860 INFO [56/100] -vxjVxOeScU/4 duration=9.127s words=21 audio=899 vision=46 errors=none time=1.4s
|
||||
2026-09-23 16:08:02,080 INFO [57/100] -wMB_hJL-3o/7 duration=6.044s words=22 audio=593 vision=31 errors=none time=1.2s
|
||||
2026-09-23 16:08:03,536 INFO [58/100] -wny0OAz3g8/1 duration=6.844s words=23 audio=673 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:08:04,711 INFO [59/100] -wny0OAz3g8/0 duration=3.333s words=9 audio=323 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:08:06,127 INFO [60/100] -wny0OAz3g8/3 duration=6.146s words=20 audio=605 vision=31 errors=none time=1.4s
|
||||
2026-09-23 16:08:07,525 INFO [61/100] -wny0OAz3g8/2 duration=6.687s words=23 audio=648 vision=33 errors=none time=1.4s
|
||||
2026-09-23 16:08:09,148 INFO [62/100] -wny0OAz3g8/5 duration=6.912s words=20 audio=670 vision=34 errors=none time=1.6s
|
||||
2026-09-23 16:08:11,731 INFO [63/100] -wny0OAz3g8/7 duration=8.068s words=29 audio=787 vision=40 errors=none time=2.6s
|
||||
2026-09-23 16:08:13,085 INFO [64/100] -wny0OAz3g8/9 duration=6.213s words=20 audio=600 vision=31 errors=none time=1.4s
|
||||
2026-09-23 16:08:14,322 INFO [65/100] -571d8cVauQ/0 duration=5.067s words=12 audio=495 vision=26 errors=none time=1.2s
|
||||
2026-09-23 16:08:16,030 INFO [66/100] -571d8cVauQ/5 duration=15.273s words=43 audio=1507 vision=76 errors=none time=1.7s
|
||||
2026-09-23 16:08:17,412 INFO [67/100] -I_e4mIh0yE/1 duration=7.622s words=18 audio=740 vision=38 errors=none time=1.4s
|
||||
2026-09-23 16:08:18,828 INFO [68/100] -I_e4mIh0yE/3 duration=9.163s words=22 audio=895 vision=46 errors=none time=1.4s
|
||||
2026-09-23 16:08:20,148 INFO [69/100] -UacrmKiTn4/10 duration=7.362s words=18 audio=720 vision=37 errors=none time=1.3s
|
||||
2026-09-23 16:08:21,326 INFO [70/100] -UacrmKiTn4/4 duration=4.741s words=14 audio=464 vision=24 errors=none time=1.2s
|
||||
2026-09-23 16:08:22,706 INFO [71/100] -hnBHBN8p5A/7 duration=7.372s words=13 audio=726 vision=36 errors=none time=1.4s
|
||||
2026-09-23 16:08:24,177 INFO [72/100] -hnBHBN8p5A/6 duration=6.401s words=13 audio=629 vision=31 errors=none time=1.5s
|
||||
2026-09-23 16:08:25,370 INFO [73/100] -qDkUB0GgYY/6 duration=4.678s words=16 audio=457 vision=24 errors=none time=1.2s
|
||||
2026-09-23 16:08:26,626 INFO [74/100] -uywlfIYOS8/4 duration=6.045s words=18 audio=584 vision=30 errors=none time=1.3s
|
||||
2026-09-23 16:08:28,197 INFO [75/100] -6rXp3zJ3kc/8 duration=12.805s words=34 audio=1269 vision=64 errors=none time=1.6s
|
||||
2026-09-23 16:08:29,681 INFO [76/100] -9y-fZ3swSY/0 duration=6.833s words=22 audio=671 vision=35 errors=none time=1.5s
|
||||
2026-09-23 16:08:30,871 INFO [77/100] -9y-fZ3swSY/4 duration=2.821s words=9 audio=262 vision=14 errors=none time=1.2s
|
||||
2026-09-23 16:08:32,337 INFO [78/100] -9y-fZ3swSY/8 duration=4.989s words=12 audio=487 vision=25 errors=none time=1.5s
|
||||
2026-09-23 16:08:34,833 INFO [79/100] -AUZQgSxyPQ/2 duration=22.511s words=41 audio=2236 vision=113 errors=none time=2.5s
|
||||
2026-09-23 16:08:36,191 INFO [80/100] -HeZS2-Prhc/2 duration=8.262s words=16 audio=811 vision=41 errors=none time=1.4s
|
||||
2026-09-23 16:08:37,629 INFO [81/100] -MeTTeMJBNc/0 duration=9.300s words=21 audio=917 vision=47 errors=none time=1.4s
|
||||
2026-09-23 16:08:38,863 INFO [82/100] -MeTTeMJBNc/13 duration=5.430s words=14 audio=521 vision=27 errors=none time=1.2s
|
||||
2026-09-23 16:08:40,363 INFO [83/100] -MeTTeMJBNc/7 duration=10.517s words=31 audio=1037 vision=53 errors=none time=1.5s
|
||||
2026-09-23 16:08:41,743 INFO [84/100] -RfYyzHpjk4/11 duration=5.239s words=17 audio=503 vision=26 errors=none time=1.4s
|
||||
2026-09-23 16:08:43,139 INFO [85/100] -RfYyzHpjk4/8 duration=4.589s words=17 audio=449 vision=23 errors=none time=1.4s
|
||||
2026-09-23 16:08:44,478 INFO [86/100] -RfYyzHpjk4/2 duration=5.516s words=25 audio=535 vision=28 errors=none time=1.3s
|
||||
2026-09-23 16:08:45,830 INFO [87/100] -UUCSKoHeMA/0 duration=7.800s words=18 audio=769 vision=39 errors=none time=1.4s
|
||||
2026-09-23 16:08:46,937 INFO [88/100] -ri04Z7vwnc/0 duration=2.807s words=8 audio=272 vision=14 errors=none time=1.1s
|
||||
2026-09-23 16:08:48,267 INFO [89/100] -ri04Z7vwnc/2 duration=6.027s words=16 audio=587 vision=29 errors=none time=1.3s
|
||||
2026-09-23 16:08:49,476 INFO [90/100] -ri04Z7vwnc/5 duration=3.545s words=9 audio=339 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:08:50,784 INFO [91/100] -s9qJ7ATP7w/1 duration=4.792s words=11 audio=460 vision=24 errors=none time=1.3s
|
||||
2026-09-23 16:08:52,242 INFO [92/100] -s9qJ7ATP7w/0 duration=6.800s words=24 audio=667 vision=34 errors=none time=1.5s
|
||||
2026-09-23 16:08:53,770 INFO [93/100] -s9qJ7ATP7w/5 duration=8.561s words=19 audio=835 vision=43 errors=none time=1.5s
|
||||
2026-09-23 16:08:55,096 INFO [94/100] -s9qJ7ATP7w/4 duration=4.427s words=9 audio=420 vision=22 errors=none time=1.3s
|
||||
2026-09-23 16:08:56,542 INFO [95/100] -s9qJ7ATP7w/7 duration=6.966s words=28 audio=679 vision=35 errors=none time=1.4s
|
||||
2026-09-23 16:08:57,714 INFO [96/100] -s9qJ7ATP7w/6 duration=2.475s words=5 audio=227 vision=12 errors=none time=1.2s
|
||||
2026-09-23 16:08:58,901 INFO [97/100] -s9qJ7ATP7w/8 duration=3.295s words=13 audio=314 vision=17 errors=none time=1.2s
|
||||
2026-09-23 16:09:01,834 INFO [98/100] -yRb-Jum7EQ/1 duration=29.288s words=49 audio=2906 vision=146 errors=none time=2.9s
|
||||
2026-09-23 16:09:03,606 INFO [99/100] -yRb-Jum7EQ/5 duration=13.169s words=25 audio=1300 vision=66 errors=none time=1.8s
|
||||
2026-09-23 16:09:05,321 INFO [100/100] -yRb-Jum7EQ/6 duration=11.242s words=19 audio=1120 vision=56 errors=none time=1.7s
|
||||
2026-09-23 16:12:18,806 INFO Using cuda
|
||||
2026-09-23 16:12:18,806 INFO Loading text model google-bert/bert-base-uncased
|
||||
2026-09-23 16:12:21,275 INFO Loading CTC model facebook/wav2vec2-base-960h
|
||||
2026-09-23 16:12:23,358 INFO Loading general vision model facebook/deit-tiny-patch16-224
|
||||
2026-09-23 16:12:26,032 INFO Feature models are ready on cuda
|
||||
2026-09-23 16:12:28,005 INFO [1/100] -3g5yACwYnA/13 duration=5.514s words=15 audio=535 vision=28 errors=none time=2.0s
|
||||
2026-09-23 16:12:29,551 INFO [2/100] -3g5yACwYnA/3 duration=14.389s words=29 audio=1428 vision=72 errors=none time=1.5s
|
||||
2026-09-23 16:12:30,761 INFO [3/100] -3g5yACwYnA/2 duration=9.394s words=14 audio=919 vision=47 errors=none time=1.2s
|
||||
2026-09-23 16:12:31,942 INFO [4/100] -3g5yACwYnA/9 duration=8.817s words=21 audio=865 vision=44 errors=none time=1.2s
|
||||
2026-09-23 16:12:32,908 INFO [5/100] -3nNcZdcdvU/5 duration=7.868s words=18 audio=774 vision=40 errors=none time=1.0s
|
||||
2026-09-23 16:12:33,894 INFO [6/100] -HwX2H8Z4hY/2 duration=3.982s words=8 audio=387 vision=20 errors=none time=1.0s
|
||||
2026-09-23 16:12:34,871 INFO [7/100] -HwX2H8Z4hY/5 duration=5.653s words=10 audio=550 vision=28 errors=none time=1.0s
|
||||
2026-09-23 16:12:35,858 INFO [8/100] -HwX2H8Z4hY/6 duration=3.358s words=7 audio=321 vision=17 errors=none time=1.0s
|
||||
2026-09-23 16:12:36,895 INFO [9/100] -HwX2H8Z4hY/9 duration=7.734s words=22 audio=759 vision=39 errors=none time=1.0s
|
||||
2026-09-23 16:12:37,867 INFO [10/100] -NFrJFQijFE/1 duration=5.746s words=16 audio=561 vision=29 errors=none time=1.0s
|
||||
2026-09-23 16:12:38,770 INFO [11/100] -NFrJFQijFE/2 duration=6.856s words=18 audio=665 vision=34 errors=none time=0.9s
|
||||
2026-09-23 16:12:40,134 INFO [12/100] -THoVjtIkeU/12 duration=14.896s words=39 audio=1476 vision=75 errors=none time=1.4s
|
||||
2026-09-23 16:12:40,932 INFO [13/100] -THoVjtIkeU/2 duration=4.292s words=10 audio=419 vision=22 errors=none time=0.8s
|
||||
2026-09-23 16:12:41,931 INFO [14/100] -THoVjtIkeU/6 duration=8.097s words=30 audio=794 vision=41 errors=none time=1.0s
|
||||
2026-09-23 16:12:43,126 INFO [15/100] -UuX1xuaiiE/1 duration=10.350s words=27 audio=1022 vision=52 errors=none time=1.2s
|
||||
2026-09-23 16:12:44,035 INFO [16/100] -UuX1xuaiiE/0 duration=3.633s words=9 audio=353 vision=19 errors=none time=0.9s
|
||||
2026-09-23 16:12:45,010 INFO [17/100] -UuX1xuaiiE/3 duration=4.130s words=9 audio=399 vision=21 errors=none time=1.0s
|
||||
2026-09-23 16:12:46,246 INFO [18/100] -UuX1xuaiiE/6 duration=8.114s words=22 audio=790 vision=40 errors=none time=1.2s
|
||||
2026-09-23 16:12:47,956 INFO [19/100] -a55Q6RWvTA/3 duration=22.154s words=65 audio=2204 vision=111 errors=none time=1.7s
|
||||
2026-09-23 16:12:48,958 INFO [20/100] -aNfi7CP8vM/7 duration=8.695s words=18 audio=849 vision=43 errors=none time=1.0s
|
||||
2026-09-23 16:12:50,312 INFO [21/100] -aqamKhZ1Ec/0 duration=10.967s words=14 audio=1085 vision=55 errors=none time=1.4s
|
||||
2026-09-23 16:12:51,643 INFO [22/100] -dxfTGcXJoc/1 duration=16.161s words=36 audio=1597 vision=81 errors=none time=1.3s
|
||||
2026-09-23 16:12:53,108 INFO [23/100] -dxfTGcXJoc/0 duration=20.500s words=41 audio=2037 vision=103 errors=none time=1.5s
|
||||
2026-09-23 16:12:54,475 INFO [24/100] -dxfTGcXJoc/2 duration=16.698s words=34 audio=1659 vision=84 errors=none time=1.4s
|
||||
2026-09-23 16:12:55,642 INFO [25/100] -dxfTGcXJoc/6 duration=12.735s words=27 audio=1258 vision=64 errors=none time=1.2s
|
||||
2026-09-23 16:12:56,579 INFO [26/100] -egA8-b7-3M/26 duration=6.031s words=15 audio=588 vision=30 errors=none time=0.9s
|
||||
2026-09-23 16:12:57,550 INFO [27/100] -egA8-b7-3M/17 duration=7.271s words=16 audio=705 vision=36 errors=none time=1.0s
|
||||
2026-09-23 16:12:58,570 INFO [28/100] -egA8-b7-3M/18 duration=8.386s words=22 audio=822 vision=42 errors=none time=1.0s
|
||||
2026-09-23 16:12:59,460 INFO [29/100] -egA8-b7-3M/16 duration=5.538s words=11 audio=544 vision=28 errors=none time=0.9s
|
||||
2026-09-23 16:13:00,300 INFO [30/100] -egA8-b7-3M/13 duration=4.184s words=11 audio=398 vision=21 errors=none time=0.8s
|
||||
2026-09-23 16:13:01,415 INFO [31/100] -egA8-b7-3M/1 duration=10.266s words=20 audio=1011 vision=51 errors=none time=1.1s
|
||||
2026-09-23 16:13:02,315 INFO [32/100] -egA8-b7-3M/6 duration=6.265s words=12 audio=614 vision=32 errors=none time=0.9s
|
||||
2026-09-23 16:13:03,183 INFO [33/100] -egA8-b7-3M/9 duration=5.090s words=10 audio=489 vision=25 errors=none time=0.9s
|
||||
2026-09-23 16:13:04,133 INFO [34/100] -egA8-b7-3M/20 duration=6.645s words=20 audio=643 vision=33 errors=none time=0.9s
|
||||
2026-09-23 16:13:05,051 INFO [35/100] -iRBcNs9oI8/3 duration=5.621s words=8 audio=549 vision=28 errors=none time=0.9s
|
||||
2026-09-23 16:13:05,863 INFO [36/100] -iRBcNs9oI8/7 duration=4.104s words=9 audio=396 vision=20 errors=none time=0.8s
|
||||
2026-09-23 16:13:06,630 INFO [37/100] -iRBcNs9oI8/6 duration=2.903s words=5 audio=278 vision=15 errors=none time=0.8s
|
||||
2026-09-23 16:13:07,446 INFO [38/100] -iRBcNs9oI8/9 duration=3.416s words=5 audio=333 vision=17 errors=none time=0.8s
|
||||
2026-09-23 16:13:08,442 INFO [39/100] -iRBcNs9oI8/8 duration=8.093s words=21 audio=798 vision=41 errors=none time=1.0s
|
||||
2026-09-23 16:13:09,496 INFO [40/100] -lzEya4AM_4/5 duration=7.675s words=19 audio=752 vision=39 errors=none time=1.1s
|
||||
2026-09-23 16:13:10,897 INFO [41/100] -lzEya4AM_4/6 duration=14.792s words=43 audio=1470 vision=74 errors=none time=1.4s
|
||||
2026-09-23 16:13:11,807 INFO [42/100] -mJ2ud6oKI8/1 duration=6.103s words=13 audio=601 vision=31 errors=none time=0.9s
|
||||
2026-09-23 16:13:12,687 INFO [43/100] -mJ2ud6oKI8/2 duration=5.731s words=11 audio=566 vision=29 errors=none time=0.9s
|
||||
2026-09-23 16:13:13,438 INFO [44/100] -mJ2ud6oKI8/6 duration=2.257s words=5 audio=218 vision=12 errors=none time=0.8s
|
||||
2026-09-23 16:13:14,572 INFO [45/100] -mJ2ud6oKI8/9 duration=7.033s words=22 audio=686 vision=35 errors=none time=1.1s
|
||||
2026-09-23 16:13:15,487 INFO [46/100] -mJ2ud6oKI8/8 duration=4.192s words=11 audio=413 vision=21 errors=none time=0.9s
|
||||
2026-09-23 16:13:16,595 INFO [47/100] -mqbVkbCndg/0 duration=6.467s words=12 audio=634 vision=33 errors=none time=1.1s
|
||||
2026-09-23 16:13:17,469 INFO [48/100] -t217m2on-s/2 duration=5.686s words=12 audio=559 vision=29 errors=none time=0.9s
|
||||
2026-09-23 16:13:18,870 INFO [49/100] -t217m2on-s/7 duration=17.183s words=45 audio=1698 vision=86 errors=none time=1.4s
|
||||
2026-09-23 16:13:20,243 INFO [50/100] -tANM6ETl_M/3 duration=6.758s words=22 audio=656 vision=34 errors=none time=1.4s
|
||||
2026-09-23 16:13:21,094 INFO [51/100] -tPCytz4rww/11 duration=5.467s words=17 audio=533 vision=28 errors=none time=0.9s
|
||||
2026-09-23 16:13:21,970 INFO [52/100] -tPCytz4rww/10 duration=4.789s words=12 audio=463 vision=24 errors=none time=0.9s
|
||||
2026-09-23 16:13:23,126 INFO [53/100] -tPCytz4rww/12 duration=11.864s words=26 audio=1169 vision=59 errors=none time=1.2s
|
||||
2026-09-23 16:13:24,059 INFO [54/100] -tPCytz4rww/16 duration=7.206s words=16 audio=709 vision=36 errors=none time=0.9s
|
||||
2026-09-23 16:13:24,979 INFO [55/100] -tPCytz4rww/18 duration=6.645s words=16 audio=652 vision=34 errors=none time=0.9s
|
||||
2026-09-23 16:13:26,002 INFO [56/100] -vxjVxOeScU/4 duration=9.127s words=21 audio=899 vision=46 errors=none time=1.0s
|
||||
2026-09-23 16:13:26,864 INFO [57/100] -wMB_hJL-3o/7 duration=6.044s words=22 audio=593 vision=31 errors=none time=0.9s
|
||||
2026-09-23 16:13:27,943 INFO [58/100] -wny0OAz3g8/1 duration=6.844s words=23 audio=673 vision=35 errors=none time=1.1s
|
||||
2026-09-23 16:13:28,799 INFO [59/100] -wny0OAz3g8/0 duration=3.333s words=9 audio=323 vision=17 errors=none time=0.9s
|
||||
2026-09-23 16:13:29,839 INFO [60/100] -wny0OAz3g8/3 duration=6.146s words=20 audio=605 vision=31 errors=none time=1.0s
|
||||
2026-09-23 16:13:30,905 INFO [61/100] -wny0OAz3g8/2 duration=6.687s words=23 audio=648 vision=33 errors=none time=1.1s
|
||||
2026-09-23 16:13:31,902 INFO [62/100] -wny0OAz3g8/5 duration=6.912s words=20 audio=670 vision=34 errors=none time=1.0s
|
||||
2026-09-23 16:13:33,026 INFO [63/100] -wny0OAz3g8/7 duration=8.068s words=29 audio=787 vision=40 errors=none time=1.1s
|
||||
2026-09-23 16:13:34,049 INFO [64/100] -wny0OAz3g8/9 duration=6.213s words=20 audio=600 vision=31 errors=none time=1.0s
|
||||
2026-09-23 16:13:34,864 INFO [65/100] -571d8cVauQ/0 duration=5.067s words=12 audio=495 vision=26 errors=none time=0.8s
|
||||
2026-09-23 16:13:36,173 INFO [66/100] -571d8cVauQ/5 duration=15.273s words=43 audio=1507 vision=76 errors=none time=1.3s
|
||||
2026-09-23 16:13:37,106 INFO [67/100] -I_e4mIh0yE/1 duration=7.622s words=18 audio=740 vision=38 errors=none time=0.9s
|
||||
2026-09-23 16:13:38,166 INFO [68/100] -I_e4mIh0yE/3 duration=9.163s words=22 audio=895 vision=46 errors=none time=1.1s
|
||||
2026-09-23 16:13:39,102 INFO [69/100] -UacrmKiTn4/10 duration=7.362s words=18 audio=720 vision=37 errors=none time=0.9s
|
||||
2026-09-23 16:13:39,901 INFO [70/100] -UacrmKiTn4/4 duration=4.741s words=14 audio=464 vision=24 errors=none time=0.8s
|
||||
2026-09-23 16:13:40,872 INFO [71/100] -hnBHBN8p5A/7 duration=7.372s words=13 audio=726 vision=36 errors=none time=1.0s
|
||||
2026-09-23 16:13:41,822 INFO [72/100] -hnBHBN8p5A/6 duration=6.401s words=13 audio=629 vision=31 errors=none time=0.9s
|
||||
2026-09-23 16:13:42,639 INFO [73/100] -qDkUB0GgYY/6 duration=4.678s words=16 audio=457 vision=24 errors=none time=0.8s
|
||||
2026-09-23 16:13:43,512 INFO [74/100] -uywlfIYOS8/4 duration=6.045s words=18 audio=584 vision=30 errors=none time=0.9s
|
||||
2026-09-23 16:13:44,755 INFO [75/100] -6rXp3zJ3kc/8 duration=12.805s words=34 audio=1269 vision=64 errors=none time=1.2s
|
||||
2026-09-23 16:13:45,838 INFO [76/100] -9y-fZ3swSY/0 duration=6.833s words=22 audio=671 vision=35 errors=none time=1.1s
|
||||
2026-09-23 16:13:46,634 INFO [77/100] -9y-fZ3swSY/4 duration=2.821s words=9 audio=262 vision=14 errors=none time=0.8s
|
||||
2026-09-23 16:13:47,648 INFO [78/100] -9y-fZ3swSY/8 duration=4.989s words=12 audio=487 vision=25 errors=none time=1.0s
|
||||
2026-09-23 16:13:49,723 INFO [79/100] -AUZQgSxyPQ/2 duration=22.511s words=41 audio=2236 vision=113 errors=none time=2.1s
|
||||
2026-09-23 16:13:50,726 INFO [80/100] -HeZS2-Prhc/2 duration=8.262s words=16 audio=811 vision=41 errors=none time=1.0s
|
||||
2026-09-23 16:13:51,775 INFO [81/100] -MeTTeMJBNc/0 duration=9.300s words=21 audio=917 vision=47 errors=none time=1.0s
|
||||
2026-09-23 16:13:52,663 INFO [82/100] -MeTTeMJBNc/13 duration=5.430s words=14 audio=521 vision=27 errors=none time=0.9s
|
||||
2026-09-23 16:13:53,848 INFO [83/100] -MeTTeMJBNc/7 duration=10.517s words=31 audio=1037 vision=53 errors=none time=1.2s
|
||||
2026-09-23 16:13:54,869 INFO [84/100] -RfYyzHpjk4/11 duration=5.239s words=17 audio=503 vision=26 errors=none time=1.0s
|
||||
2026-09-23 16:13:55,863 INFO [85/100] -RfYyzHpjk4/8 duration=4.589s words=17 audio=449 vision=23 errors=none time=1.0s
|
||||
2026-09-23 16:13:56,823 INFO [86/100] -RfYyzHpjk4/2 duration=5.516s words=25 audio=535 vision=28 errors=none time=1.0s
|
||||
2026-09-23 16:13:57,798 INFO [87/100] -UUCSKoHeMA/0 duration=7.800s words=18 audio=769 vision=39 errors=none time=1.0s
|
||||
2026-09-23 16:13:58,544 INFO [88/100] -ri04Z7vwnc/0 duration=2.807s words=8 audio=272 vision=14 errors=none time=0.7s
|
||||
2026-09-23 16:13:59,439 INFO [89/100] -ri04Z7vwnc/2 duration=6.027s words=16 audio=587 vision=29 errors=none time=0.9s
|
||||
2026-09-23 16:14:00,294 INFO [90/100] -ri04Z7vwnc/5 duration=3.545s words=9 audio=339 vision=17 errors=none time=0.9s
|
||||
2026-09-23 16:14:01,236 INFO [91/100] -s9qJ7ATP7w/1 duration=4.792s words=11 audio=460 vision=24 errors=none time=0.9s
|
||||
2026-09-23 16:14:03,378 INFO [92/100] -s9qJ7ATP7w/0 duration=6.800s words=24 audio=667 vision=34 errors=none time=2.1s
|
||||
2026-09-23 16:14:04,656 INFO [93/100] -s9qJ7ATP7w/5 duration=8.561s words=19 audio=835 vision=43 errors=none time=1.3s
|
||||
2026-09-23 16:14:05,567 INFO [94/100] -s9qJ7ATP7w/4 duration=4.427s words=9 audio=420 vision=22 errors=none time=0.9s
|
||||
2026-09-23 16:14:06,643 INFO [95/100] -s9qJ7ATP7w/7 duration=6.966s words=28 audio=679 vision=35 errors=none time=1.1s
|
||||
2026-09-23 16:14:07,447 INFO [96/100] -s9qJ7ATP7w/6 duration=2.475s words=5 audio=227 vision=12 errors=none time=0.8s
|
||||
2026-09-23 16:14:08,310 INFO [97/100] -s9qJ7ATP7w/8 duration=3.295s words=13 audio=314 vision=17 errors=none time=0.9s
|
||||
2026-09-23 16:14:10,833 INFO [98/100] -yRb-Jum7EQ/1 duration=29.288s words=49 audio=2906 vision=146 errors=none time=2.5s
|
||||
2026-09-23 16:14:12,243 INFO [99/100] -yRb-Jum7EQ/5 duration=13.169s words=25 audio=1300 vision=66 errors=none time=1.4s
|
||||
2026-09-23 16:14:13,679 INFO [100/100] -yRb-Jum7EQ/6 duration=11.242s words=19 audio=1120 vision=56 errors=none time=1.4s
|
||||
2026-09-23 16:17:58,104 INFO Using cuda
|
||||
2026-09-23 16:17:58,105 INFO Loading text model google-bert/bert-base-uncased
|
||||
2026-09-23 16:18:00,556 INFO Loading CTC model facebook/wav2vec2-base-960h
|
||||
2026-09-23 16:18:02,582 INFO Loading general vision model facebook/deit-tiny-patch16-224
|
||||
2026-09-23 16:18:05,282 INFO Feature models are ready on cuda
|
||||
2026-09-23 16:18:05,283 INFO [1/100] resume existing -3g5yACwYnA/13
|
||||
2026-09-23 16:18:05,283 INFO [2/100] resume existing -3g5yACwYnA/3
|
||||
2026-09-23 16:18:05,283 INFO [3/100] resume existing -3g5yACwYnA/2
|
||||
2026-09-23 16:18:05,283 INFO [4/100] resume existing -3g5yACwYnA/9
|
||||
2026-09-23 16:18:05,283 INFO [5/100] resume existing -3nNcZdcdvU/5
|
||||
2026-09-23 16:18:05,283 INFO [6/100] resume existing -HwX2H8Z4hY/2
|
||||
2026-09-23 16:18:05,283 INFO [7/100] resume existing -HwX2H8Z4hY/5
|
||||
2026-09-23 16:18:05,284 INFO [8/100] resume existing -HwX2H8Z4hY/6
|
||||
2026-09-23 16:18:05,284 INFO [9/100] resume existing -HwX2H8Z4hY/9
|
||||
2026-09-23 16:18:05,284 INFO [10/100] resume existing -NFrJFQijFE/1
|
||||
2026-09-23 16:18:05,284 INFO [11/100] resume existing -NFrJFQijFE/2
|
||||
2026-09-23 16:18:05,284 INFO [12/100] resume existing -THoVjtIkeU/12
|
||||
2026-09-23 16:18:05,284 INFO [13/100] resume existing -THoVjtIkeU/2
|
||||
2026-09-23 16:18:05,284 INFO [14/100] resume existing -THoVjtIkeU/6
|
||||
2026-09-23 16:18:05,284 INFO [15/100] resume existing -UuX1xuaiiE/1
|
||||
2026-09-23 16:18:05,285 INFO [16/100] resume existing -UuX1xuaiiE/0
|
||||
2026-09-23 16:18:05,285 INFO [17/100] resume existing -UuX1xuaiiE/3
|
||||
2026-09-23 16:18:05,285 INFO [18/100] resume existing -UuX1xuaiiE/6
|
||||
2026-09-23 16:18:05,285 INFO [19/100] resume existing -a55Q6RWvTA/3
|
||||
2026-09-23 16:18:05,285 INFO [20/100] resume existing -aNfi7CP8vM/7
|
||||
2026-09-23 16:18:05,285 INFO [21/100] resume existing -aqamKhZ1Ec/0
|
||||
2026-09-23 16:18:05,285 INFO [22/100] resume existing -dxfTGcXJoc/1
|
||||
2026-09-23 16:18:05,285 INFO [23/100] resume existing -dxfTGcXJoc/0
|
||||
2026-09-23 16:18:05,286 INFO [24/100] resume existing -dxfTGcXJoc/2
|
||||
2026-09-23 16:18:05,286 INFO [25/100] resume existing -dxfTGcXJoc/6
|
||||
2026-09-23 16:18:05,286 INFO [26/100] resume existing -egA8-b7-3M/26
|
||||
2026-09-23 16:18:05,286 INFO [27/100] resume existing -egA8-b7-3M/17
|
||||
2026-09-23 16:18:05,286 INFO [28/100] resume existing -egA8-b7-3M/18
|
||||
2026-09-23 16:18:05,286 INFO [29/100] resume existing -egA8-b7-3M/16
|
||||
2026-09-23 16:18:05,286 INFO [30/100] resume existing -egA8-b7-3M/13
|
||||
2026-09-23 16:18:05,286 INFO [31/100] resume existing -egA8-b7-3M/1
|
||||
2026-09-23 16:18:05,286 INFO [32/100] resume existing -egA8-b7-3M/6
|
||||
2026-09-23 16:18:05,287 INFO [33/100] resume existing -egA8-b7-3M/9
|
||||
2026-09-23 16:18:05,287 INFO [34/100] resume existing -egA8-b7-3M/20
|
||||
2026-09-23 16:18:05,287 INFO [35/100] resume existing -iRBcNs9oI8/3
|
||||
2026-09-23 16:18:05,287 INFO [36/100] resume existing -iRBcNs9oI8/7
|
||||
2026-09-23 16:18:05,287 INFO [37/100] resume existing -iRBcNs9oI8/6
|
||||
2026-09-23 16:18:05,287 INFO [38/100] resume existing -iRBcNs9oI8/9
|
||||
2026-09-23 16:18:05,287 INFO [39/100] resume existing -iRBcNs9oI8/8
|
||||
2026-09-23 16:18:05,287 INFO [40/100] resume existing -lzEya4AM_4/5
|
||||
2026-09-23 16:18:05,288 INFO [41/100] resume existing -lzEya4AM_4/6
|
||||
2026-09-23 16:18:05,288 INFO [42/100] resume existing -mJ2ud6oKI8/1
|
||||
2026-09-23 16:18:05,288 INFO [43/100] resume existing -mJ2ud6oKI8/2
|
||||
2026-09-23 16:18:05,288 INFO [44/100] resume existing -mJ2ud6oKI8/6
|
||||
2026-09-23 16:18:05,288 INFO [45/100] resume existing -mJ2ud6oKI8/9
|
||||
2026-09-23 16:18:05,288 INFO [46/100] resume existing -mJ2ud6oKI8/8
|
||||
2026-09-23 16:18:05,288 INFO [47/100] resume existing -mqbVkbCndg/0
|
||||
2026-09-23 16:18:05,288 INFO [48/100] resume existing -t217m2on-s/2
|
||||
2026-09-23 16:18:05,288 INFO [49/100] resume existing -t217m2on-s/7
|
||||
2026-09-23 16:18:05,289 INFO [50/100] resume existing -tANM6ETl_M/3
|
||||
2026-09-23 16:18:05,289 INFO [51/100] resume existing -tPCytz4rww/11
|
||||
2026-09-23 16:18:05,289 INFO [52/100] resume existing -tPCytz4rww/10
|
||||
2026-09-23 16:18:05,289 INFO [53/100] resume existing -tPCytz4rww/12
|
||||
2026-09-23 16:18:05,289 INFO [54/100] resume existing -tPCytz4rww/16
|
||||
2026-09-23 16:18:05,289 INFO [55/100] resume existing -tPCytz4rww/18
|
||||
2026-09-23 16:18:05,289 INFO [56/100] resume existing -vxjVxOeScU/4
|
||||
2026-09-23 16:18:05,289 INFO [57/100] resume existing -wMB_hJL-3o/7
|
||||
2026-09-23 16:18:05,290 INFO [58/100] resume existing -wny0OAz3g8/1
|
||||
2026-09-23 16:18:05,290 INFO [59/100] resume existing -wny0OAz3g8/0
|
||||
2026-09-23 16:18:05,290 INFO [60/100] resume existing -wny0OAz3g8/3
|
||||
2026-09-23 16:18:05,290 INFO [61/100] resume existing -wny0OAz3g8/2
|
||||
2026-09-23 16:18:05,290 INFO [62/100] resume existing -wny0OAz3g8/5
|
||||
2026-09-23 16:18:05,290 INFO [63/100] resume existing -wny0OAz3g8/7
|
||||
2026-09-23 16:18:05,290 INFO [64/100] resume existing -wny0OAz3g8/9
|
||||
2026-09-23 16:18:05,290 INFO [65/100] resume existing -571d8cVauQ/0
|
||||
2026-09-23 16:18:05,290 INFO [66/100] resume existing -571d8cVauQ/5
|
||||
2026-09-23 16:18:05,291 INFO [67/100] resume existing -I_e4mIh0yE/1
|
||||
2026-09-23 16:18:05,291 INFO [68/100] resume existing -I_e4mIh0yE/3
|
||||
2026-09-23 16:18:05,291 INFO [69/100] resume existing -UacrmKiTn4/10
|
||||
2026-09-23 16:18:05,291 INFO [70/100] resume existing -UacrmKiTn4/4
|
||||
2026-09-23 16:18:05,291 INFO [71/100] resume existing -hnBHBN8p5A/7
|
||||
2026-09-23 16:18:05,291 INFO [72/100] resume existing -hnBHBN8p5A/6
|
||||
2026-09-23 16:18:05,291 INFO [73/100] resume existing -qDkUB0GgYY/6
|
||||
2026-09-23 16:18:05,291 INFO [74/100] resume existing -uywlfIYOS8/4
|
||||
2026-09-23 16:18:05,292 INFO [75/100] resume existing -6rXp3zJ3kc/8
|
||||
2026-09-23 16:18:05,292 INFO [76/100] resume existing -9y-fZ3swSY/0
|
||||
2026-09-23 16:18:05,292 INFO [77/100] resume existing -9y-fZ3swSY/4
|
||||
2026-09-23 16:18:05,292 INFO [78/100] resume existing -9y-fZ3swSY/8
|
||||
2026-09-23 16:18:05,292 INFO [79/100] resume existing -AUZQgSxyPQ/2
|
||||
2026-09-23 16:18:05,292 INFO [80/100] resume existing -HeZS2-Prhc/2
|
||||
2026-09-23 16:18:05,292 INFO [81/100] resume existing -MeTTeMJBNc/0
|
||||
2026-09-23 16:18:05,292 INFO [82/100] resume existing -MeTTeMJBNc/13
|
||||
2026-09-23 16:18:05,293 INFO [83/100] resume existing -MeTTeMJBNc/7
|
||||
2026-09-23 16:18:05,293 INFO [84/100] resume existing -RfYyzHpjk4/11
|
||||
2026-09-23 16:18:05,293 INFO [85/100] resume existing -RfYyzHpjk4/8
|
||||
2026-09-23 16:18:05,293 INFO [86/100] resume existing -RfYyzHpjk4/2
|
||||
2026-09-23 16:18:05,293 INFO [87/100] resume existing -UUCSKoHeMA/0
|
||||
2026-09-23 16:18:05,293 INFO [88/100] resume existing -ri04Z7vwnc/0
|
||||
2026-09-23 16:18:05,293 INFO [89/100] resume existing -ri04Z7vwnc/2
|
||||
2026-09-23 16:18:05,293 INFO [90/100] resume existing -ri04Z7vwnc/5
|
||||
2026-09-23 16:18:05,293 INFO [91/100] resume existing -s9qJ7ATP7w/1
|
||||
2026-09-23 16:18:05,294 INFO [92/100] resume existing -s9qJ7ATP7w/0
|
||||
2026-09-23 16:18:05,294 INFO [93/100] resume existing -s9qJ7ATP7w/5
|
||||
2026-09-23 16:18:05,294 INFO [94/100] resume existing -s9qJ7ATP7w/4
|
||||
2026-09-23 16:18:05,294 INFO [95/100] resume existing -s9qJ7ATP7w/7
|
||||
2026-09-23 16:18:05,294 INFO [96/100] resume existing -s9qJ7ATP7w/6
|
||||
2026-09-23 16:18:05,294 INFO [97/100] resume existing -s9qJ7ATP7w/8
|
||||
2026-09-23 16:18:05,294 INFO [98/100] resume existing -yRb-Jum7EQ/1
|
||||
2026-09-23 16:18:05,294 INFO [99/100] resume existing -yRb-Jum7EQ/5
|
||||
2026-09-23 16:18:05,294 INFO [100/100] resume existing -yRb-Jum7EQ/6
|
||||
@@ -0,0 +1,100 @@
|
||||
{"sample_id": "-3g5yACwYnA/13", "video_id": "-3g5yACwYnA", "clip_id": "13", "text": "They've been able to find solutions or at least bring some answers to the table.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-3g5yACwYnA/13.mp4", "duration_s": 5.513997, "ctc_inference_succeeded": true, "word_count": 15, "word_alignment_valid_count": 15, "audio_raw_length": 535, "audio_valid_length": 535, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 28, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 163, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.972, "feature_file": "outputs/q1_features/features/-3g5yACwYnA__13.npz", "feature_file_bytes": 70429, "feature_file_sha256": "09e5e19910ce263a86e632a3bfa604775524434a4244072d28a0b7db2510a433"}
|
||||
{"sample_id": "-3g5yACwYnA/3", "video_id": "-3g5yACwYnA", "clip_id": "3", "text": "We're a huge user of adhesives for our operation, called flocking, and we don't have the technical inside compounding or the technical expertise to do these types of things.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-3g5yACwYnA/3.mp4", "duration_s": 14.388997, "ctc_inference_succeeded": true, "word_count": 29, "word_alignment_valid_count": 29, "audio_raw_length": 1428, "audio_valid_length": 1428, "audio_feature_dim": 25, "vision_raw_length": 72, "vision_valid_length": 72, "vision_feature_dim": 192, "face_blendshape_valid_length": 72, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 431, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.546, "feature_file": "outputs/q1_features/features/-3g5yACwYnA__3.npz", "feature_file_bytes": 153606, "feature_file_sha256": "3f7949f71a3c93295c6d5bb75177da024923d22abc18bc59b2799b50e9258104"}
|
||||
{"sample_id": "-3g5yACwYnA/2", "video_id": "-3g5yACwYnA", "clip_id": "2", "text": "Key Polymer brings a technical aspect to our operation that we don't have internally.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-3g5yACwYnA/2.mp4", "duration_s": 9.39401, "ctc_inference_succeeded": true, "word_count": 14, "word_alignment_valid_count": 14, "audio_raw_length": 919, "audio_valid_length": 919, "audio_feature_dim": 25, "vision_raw_length": 47, "vision_valid_length": 47, "vision_feature_dim": 192, "face_blendshape_valid_length": 47, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 278, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.209, "feature_file": "outputs/q1_features/features/-3g5yACwYnA__2.npz", "feature_file_bytes": 93925, "feature_file_sha256": "e94777084a053c5fe7eaaec3d9fb1ac5c9a14712030ed773a00fc168e3ea8236"}
|
||||
{"sample_id": "-3g5yACwYnA/9", "video_id": "-3g5yACwYnA", "clip_id": "9", "text": "We have many new opportunities through the way things have changed through the years, looking for new niche high-end, value-added products.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-3g5yACwYnA/9.mp4", "duration_s": 8.816992, "ctc_inference_succeeded": true, "word_count": 21, "word_alignment_valid_count": 21, "audio_raw_length": 865, "audio_valid_length": 865, "audio_feature_dim": 25, "vision_raw_length": 44, "vision_valid_length": 44, "vision_feature_dim": 192, "face_blendshape_valid_length": 44, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 263, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.181, "feature_file": "outputs/q1_features/features/-3g5yACwYnA__9.npz", "feature_file_bytes": 104222, "feature_file_sha256": "828ad04290ecb09981a500171d5ff9d34dc080951b32cdd41ef525aa50e79ab6"}
|
||||
{"sample_id": "-3nNcZdcdvU/5", "video_id": "-3nNcZdcdvU", "clip_id": "5", "text": "Noncompliance can result in legal liability to you and to the school district in which you are employed.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-3nNcZdcdvU/5.mp4", "duration_s": 7.867969, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 774, "audio_valid_length": 774, "audio_feature_dim": 25, "vision_raw_length": 40, "vision_valid_length": 40, "vision_feature_dim": 192, "face_blendshape_valid_length": 40, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 236, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.966, "feature_file": "outputs/q1_features/features/-3nNcZdcdvU__5.npz", "feature_file_bytes": 92502, "feature_file_sha256": "4c00de5bef73b6668cea6999aea1a3dac6da5414a03dfc101d29256d05ad147e"}
|
||||
{"sample_id": "-HwX2H8Z4hY/2", "video_id": "-HwX2H8Z4hY", "clip_id": "2", "text": "” [President Ronald Reagan:] \"Look at the record", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-HwX2H8Z4hY/2.mp4", "duration_s": 3.982031, "ctc_inference_succeeded": true, "word_count": 8, "word_alignment_valid_count": 7, "audio_raw_length": 387, "audio_valid_length": 387, "audio_feature_dim": 25, "vision_raw_length": 20, "vision_valid_length": 20, "vision_feature_dim": 192, "face_blendshape_valid_length": 4, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 119, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 0.986, "feature_file": "outputs/q1_features/features/-HwX2H8Z4hY__2.npz", "feature_file_bytes": 44625, "feature_file_sha256": "51f8ecd331cf67b2e813396c4dcc83253226a4641e9a90ce9efc530d3b63e011"}
|
||||
{"sample_id": "-HwX2H8Z4hY/5", "video_id": "-HwX2H8Z4hY", "clip_id": "5", "text": "\" President Ronald Reagan blamed the professional bureaucracy of education", "label": -1.0, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-HwX2H8Z4hY/5.mp4", "duration_s": 5.652995, "ctc_inference_succeeded": true, "word_count": 10, "word_alignment_valid_count": 9, "audio_raw_length": 550, "audio_valid_length": 550, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 7, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 168, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 0.977, "feature_file": "outputs/q1_features/features/-HwX2H8Z4hY__5.npz", "feature_file_bytes": 60515, "feature_file_sha256": "318a511a7ab864754fa58f1478d089e8e2656b744632df535052d9fe236f4cf6"}
|
||||
{"sample_id": "-HwX2H8Z4hY/6", "video_id": "-HwX2H8Z4hY", "clip_id": "6", "text": "And in part, Al Shanker did too", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-HwX2H8Z4hY/6.mp4", "duration_s": 3.358008, "ctc_inference_succeeded": true, "word_count": 7, "word_alignment_valid_count": 7, "audio_raw_length": 321, "audio_valid_length": 321, "audio_feature_dim": 25, "vision_raw_length": 17, "vision_valid_length": 17, "vision_feature_dim": 192, "face_blendshape_valid_length": 8, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 99, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.986, "feature_file": "outputs/q1_features/features/-HwX2H8Z4hY__6.npz", "feature_file_bytes": 40308, "feature_file_sha256": "e93f3b906d441fb9f46c1282d9d1317b2359dcce773ace2a9d1918e57d53aac0"}
|
||||
{"sample_id": "-HwX2H8Z4hY/9", "video_id": "-HwX2H8Z4hY", "clip_id": "9", "text": "It is a word which the administrator uses when he turns around anything which he doesn't like that the teacher is doing", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-HwX2H8Z4hY/9.mp4", "duration_s": 7.733984, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 759, "audio_valid_length": 759, "audio_feature_dim": 25, "vision_raw_length": 39, "vision_valid_length": 39, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 232, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 1.036, "feature_file": "outputs/q1_features/features/-HwX2H8Z4hY__9.npz", "feature_file_bytes": 94012, "feature_file_sha256": "bc986a6a973cf20054c4f9c32f150f91904b1e867b8edb62c43dfd692e70d52d"}
|
||||
{"sample_id": "-NFrJFQijFE/1", "video_id": "-NFrJFQijFE", "clip_id": "1", "text": "Structural mounts inside have to be properly stress analyzed so we make sure all that happens", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-NFrJFQijFE/1.mp4", "duration_s": 5.746, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 561, "audio_valid_length": 561, "audio_feature_dim": 25, "vision_raw_length": 29, "vision_valid_length": 29, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 142, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.972, "feature_file": "outputs/q1_features/features/-NFrJFQijFE__1.npz", "feature_file_bytes": 65573, "feature_file_sha256": "c7c5851bb9f0ea3ff77762b19f59c63dc3835b16bf97151cdba94b58d4f37152"}
|
||||
{"sample_id": "-NFrJFQijFE/2", "video_id": "-NFrJFQijFE", "clip_id": "2", "text": "So we coordinate with all the proper technical fields to get ready for the instrument to arrive here", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-NFrJFQijFE/2.mp4", "duration_s": 6.856, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 665, "audio_valid_length": 665, "audio_feature_dim": 25, "vision_raw_length": 34, "vision_valid_length": 34, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 169, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.902, "feature_file": "outputs/q1_features/features/-NFrJFQijFE__2.npz", "feature_file_bytes": 74682, "feature_file_sha256": "24580a879c451f3b493bb2862b702bc11876bd7e92f6ce5cdeaa63d7f3553562"}
|
||||
{"sample_id": "-THoVjtIkeU/12", "video_id": "-THoVjtIkeU", "clip_id": "12", "text": "What ever we turn our attention to is what grows and so if we believe that anything is possible, if we believe that social justice can be achieved and if we believe in youth, they will believe in themselves.", "label": 2.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-THoVjtIkeU/12.mp4", "duration_s": 14.896029, "ctc_inference_succeeded": true, "word_count": 39, "word_alignment_valid_count": 39, "audio_raw_length": 1476, "audio_valid_length": 1476, "audio_feature_dim": 25, "vision_raw_length": 75, "vision_valid_length": 75, "vision_feature_dim": 192, "face_blendshape_valid_length": 75, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 445, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.364, "feature_file": "outputs/q1_features/features/-THoVjtIkeU__12.npz", "feature_file_bytes": 175729, "feature_file_sha256": "c6d02ee1da7b846eb2d0e99396488c56156e4da84ede81b9cd5001e032111ac1"}
|
||||
{"sample_id": "-THoVjtIkeU/2", "video_id": "-THoVjtIkeU", "clip_id": "2", "text": "I think social justice is extremely important for young people.", "label": 1.3333333730697632, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-THoVjtIkeU/2.mp4", "duration_s": 4.291992, "ctc_inference_succeeded": true, "word_count": 10, "word_alignment_valid_count": 10, "audio_raw_length": 419, "audio_valid_length": 419, "audio_feature_dim": 25, "vision_raw_length": 22, "vision_valid_length": 22, "vision_feature_dim": 192, "face_blendshape_valid_length": 22, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 128, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.797, "feature_file": "outputs/q1_features/features/-THoVjtIkeU__2.npz", "feature_file_bytes": 54279, "feature_file_sha256": "89a34b5dc46d15f3e7e46c1e139cf700945bd87dce4842c52ffd3807f237e1c4"}
|
||||
{"sample_id": "-THoVjtIkeU/6", "video_id": "-THoVjtIkeU", "clip_id": "6", "text": "You know that I think listening to young people, taking in what they have to say because what we have seen all around the world is the power of youth.", "label": 2.6666667461395264, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-THoVjtIkeU/6.mp4", "duration_s": 8.097005, "ctc_inference_succeeded": true, "word_count": 30, "word_alignment_valid_count": 30, "audio_raw_length": 794, "audio_valid_length": 794, "audio_feature_dim": 25, "vision_raw_length": 41, "vision_valid_length": 41, "vision_feature_dim": 192, "face_blendshape_valid_length": 41, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 241, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.999, "feature_file": "outputs/q1_features/features/-THoVjtIkeU__6.npz", "feature_file_bytes": 116720, "feature_file_sha256": "fea5cbe0e2f40b280bd1ae100283ab60b0fe89bec42c26af3fafca30ed1751b5"}
|
||||
{"sample_id": "-UuX1xuaiiE/1", "video_id": "-UuX1xuaiiE", "clip_id": "1", "text": "^And all of them are really being able to explore ^these different areas in depth ^in a way that really wasn't available ^before the center was here", "label": 1.6666666269302368, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UuX1xuaiiE/1.mp4", "duration_s": 10.35, "ctc_inference_succeeded": true, "word_count": 27, "word_alignment_valid_count": 27, "audio_raw_length": 1022, "audio_valid_length": 1022, "audio_feature_dim": 25, "vision_raw_length": 52, "vision_valid_length": 52, "vision_feature_dim": 192, "face_blendshape_valid_length": 2, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 309, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.194, "feature_file": "outputs/q1_features/features/-UuX1xuaiiE__1.npz", "feature_file_bytes": 117161, "feature_file_sha256": "abcdcad3220fa8496b4dc85068ad7dd20a67a3bf65af69e9ab701f268138b656"}
|
||||
{"sample_id": "-UuX1xuaiiE/0", "video_id": "-UuX1xuaiiE", "clip_id": "0", "text": "^it's amazing to see their enthusiasm and their passion", "label": 2.6666667461395264, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UuX1xuaiiE/0.mp4", "duration_s": 3.633333, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 353, "audio_valid_length": 353, "audio_feature_dim": 25, "vision_raw_length": 19, "vision_valid_length": 19, "vision_feature_dim": 192, "face_blendshape_valid_length": 9, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 109, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.909, "feature_file": "outputs/q1_features/features/-UuX1xuaiiE__0.npz", "feature_file_bytes": 47230, "feature_file_sha256": "2927edadb14c25a8eff9afaba1709d2200051fe93acb43c6e0a64b10d7591db6"}
|
||||
{"sample_id": "-UuX1xuaiiE/3", "video_id": "-UuX1xuaiiE", "clip_id": "3", "text": "My goal is to become a human rights lawyer", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UuX1xuaiiE/3.mp4", "duration_s": 4.130013, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 399, "audio_valid_length": 399, "audio_feature_dim": 25, "vision_raw_length": 21, "vision_valid_length": 21, "vision_feature_dim": 192, "face_blendshape_valid_length": 20, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 123, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.975, "feature_file": "outputs/q1_features/features/-UuX1xuaiiE__3.npz", "feature_file_bytes": 51645, "feature_file_sha256": "50d511960c85926f0d19870832b54c12458d3776c2b4dc1a3821dc95868fd51d"}
|
||||
{"sample_id": "-UuX1xuaiiE/6", "video_id": "-UuX1xuaiiE", "clip_id": "6", "text": "I ended up going to work for the US government as an intelligence analyst, specializing in war crimes and human rights issues", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UuX1xuaiiE/6.mp4", "duration_s": 8.113997, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 790, "audio_valid_length": 790, "audio_feature_dim": 25, "vision_raw_length": 40, "vision_valid_length": 40, "vision_feature_dim": 192, "face_blendshape_valid_length": 39, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 240, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.236, "feature_file": "outputs/q1_features/features/-UuX1xuaiiE__6.npz", "feature_file_bytes": 100158, "feature_file_sha256": "286ee70f12631b89b435a7883f2043c0cae0b8378d6d46f9db258fd5af391b19"}
|
||||
{"sample_id": "-a55Q6RWvTA/3", "video_id": "-a55Q6RWvTA", "clip_id": "3", "text": "And if you clip coupons, if you don't go out for dinner and movies and things of that nature and try to take up things in life that, well, they always say, \"the best things in life are free\". Reading a book, going for a nice walk, and, of course, combining exercise and various things of that nature where you're not spending money per se.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-a55Q6RWvTA/3.mp4", "duration_s": 22.153971, "ctc_inference_succeeded": true, "word_count": 65, "word_alignment_valid_count": 65, "audio_raw_length": 2204, "audio_valid_length": 2204, "audio_feature_dim": 25, "vision_raw_length": 111, "vision_valid_length": 111, "vision_feature_dim": 192, "face_blendshape_valid_length": 111, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 664, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.709, "feature_file": "outputs/q1_features/features/-a55Q6RWvTA__3.npz", "feature_file_bytes": 275958, "feature_file_sha256": "2e9c79f654bf8363c47269b3a515a95a87e5f6349c6dc9301e577ea8677d009e"}
|
||||
{"sample_id": "-aNfi7CP8vM/7", "video_id": "-aNfi7CP8vM", "clip_id": "7", "text": "Maybe they have no political party affiliation, they're not interested in politics, they could care less about politics.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-aNfi7CP8vM/7.mp4", "duration_s": 8.694987, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 849, "audio_valid_length": 849, "audio_feature_dim": 25, "vision_raw_length": 43, "vision_valid_length": 43, "vision_feature_dim": 192, "face_blendshape_valid_length": 43, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 257, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.001, "feature_file": "outputs/q1_features/features/-aNfi7CP8vM__7.npz", "feature_file_bytes": 98603, "feature_file_sha256": "3bab90196a7f22dbdb6d5bb374839b2447eb416eec30377b2604af65f5facddd"}
|
||||
{"sample_id": "-aqamKhZ1Ec/0", "video_id": "-aqamKhZ1Ec", "clip_id": "0", "text": "In 2008, there were very serious tribal warfare in Kenya following a disputed election.", "label": -2.0, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-aqamKhZ1Ec/0.mp4", "duration_s": 10.966667, "ctc_inference_succeeded": true, "word_count": 14, "word_alignment_valid_count": 13, "audio_raw_length": 1085, "audio_valid_length": 1085, "audio_feature_dim": 25, "vision_raw_length": 55, "vision_valid_length": 55, "vision_feature_dim": 192, "face_blendshape_valid_length": 55, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 329, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 1.354, "feature_file": "outputs/q1_features/features/-aqamKhZ1Ec__0.npz", "feature_file_bytes": 101705, "feature_file_sha256": "eb71cd9c477f012f3b16574c1be5283fa0870dcb5d9ebc831bd6eefc2a520647"}
|
||||
{"sample_id": "-dxfTGcXJoc/1", "video_id": "-dxfTGcXJoc", "clip_id": "1", "text": "For the 10th straight year, some of Kentucky’s best and most innovative biotech companies and technologies were on display at the annual BIO International Convention, which I and other state officials attended this week in Chicago.", "label": 1.6666666269302368, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-dxfTGcXJoc/1.mp4", "duration_s": 16.161003, "ctc_inference_succeeded": true, "word_count": 36, "word_alignment_valid_count": 36, "audio_raw_length": 1597, "audio_valid_length": 1597, "audio_feature_dim": 25, "vision_raw_length": 81, "vision_valid_length": 81, "vision_feature_dim": 192, "face_blendshape_valid_length": 81, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 482, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.331, "feature_file": "outputs/q1_features/features/-dxfTGcXJoc__1.npz", "feature_file_bytes": 180363, "feature_file_sha256": "16baaa788568929e7acfcc0fc153f1fa91110e51b64263284337b87dba696dd2"}
|
||||
{"sample_id": "-dxfTGcXJoc/0", "video_id": "-dxfTGcXJoc", "clip_id": "0", "text": "This is Governor Steve Beshear ... About Kentucky Our state is home to more than 1,500 bioscience and lifescience companies and more than 100,000 people who work for these firms, in areas from nutrigenomics and pharmaceuticals to nanotechnology and medical devices.", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-dxfTGcXJoc/0.mp4", "duration_s": 20.5, "ctc_inference_succeeded": true, "word_count": 41, "word_alignment_valid_count": 38, "audio_raw_length": 2037, "audio_valid_length": 2037, "audio_feature_dim": 25, "vision_raw_length": 103, "vision_valid_length": 103, "vision_feature_dim": 192, "face_blendshape_valid_length": 80, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 615, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:3"], "processing_seconds": 1.464, "feature_file": "outputs/q1_features/features/-dxfTGcXJoc__0.npz", "feature_file_bytes": 202759, "feature_file_sha256": "ec0dda97730b66a051b03048c06c5e5d38526547f272306d94f2bbc9e5d9e90e"}
|
||||
{"sample_id": "-dxfTGcXJoc/2", "video_id": "-dxfTGcXJoc", "clip_id": "2", "text": "An estimated 20,000 biotech scientists, executives and industry experts from more than 50 nations were at the BIO conference to learn about the latest scientific advances, and to exchange ideas and establish business relationships.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-dxfTGcXJoc/2.mp4", "duration_s": 16.697982, "ctc_inference_succeeded": true, "word_count": 34, "word_alignment_valid_count": 32, "audio_raw_length": 1659, "audio_valid_length": 1659, "audio_feature_dim": 25, "vision_raw_length": 84, "vision_valid_length": 84, "vision_feature_dim": 192, "face_blendshape_valid_length": 84, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 500, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:2"], "processing_seconds": 1.367, "feature_file": "outputs/q1_features/features/-dxfTGcXJoc__2.npz", "feature_file_bytes": 180106, "feature_file_sha256": "22e90ee76842480d82da653934ed53c917b14c3131b9400b0098544f2867ac14"}
|
||||
{"sample_id": "-dxfTGcXJoc/6", "video_id": "-dxfTGcXJoc", "clip_id": "6", "text": "Kentucky’s participation at the annual BIO International Convention is the primary means by which our high-tech companies and institutions can reach out to the global scientific community.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-dxfTGcXJoc/6.mp4", "duration_s": 12.735026, "ctc_inference_succeeded": true, "word_count": 27, "word_alignment_valid_count": 27, "audio_raw_length": 1258, "audio_valid_length": 1258, "audio_feature_dim": 25, "vision_raw_length": 64, "vision_valid_length": 64, "vision_feature_dim": 192, "face_blendshape_valid_length": 63, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 381, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.167, "feature_file": "outputs/q1_features/features/-dxfTGcXJoc__6.npz", "feature_file_bytes": 140160, "feature_file_sha256": "a9457477432872f265c5efd013c19ea478198eef22302f3d9e0d96aeab7986c1"}
|
||||
{"sample_id": "-egA8-b7-3M/26", "video_id": "-egA8-b7-3M", "clip_id": "26", "text": "We're updating it all the time and looking forward to your comments on our videos.", "label": 1.6666666269302368, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/26.mp4", "duration_s": 6.03099, "ctc_inference_succeeded": true, "word_count": 15, "word_alignment_valid_count": 15, "audio_raw_length": 588, "audio_valid_length": 588, "audio_feature_dim": 25, "vision_raw_length": 30, "vision_valid_length": 30, "vision_feature_dim": 192, "face_blendshape_valid_length": 30, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 179, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.937, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__26.npz", "feature_file_bytes": 75011, "feature_file_sha256": "bf014b51b21ea87994ee21f03db87ceb5b9928eed1d2d55784790b1040af9337"}
|
||||
{"sample_id": "-egA8-b7-3M/17", "video_id": "-egA8-b7-3M", "clip_id": "17", "text": "As you have more experience, you have more times exhibiting, you get to know more people.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/17.mp4", "duration_s": 7.271029, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 705, "audio_valid_length": 705, "audio_feature_dim": 25, "vision_raw_length": 36, "vision_valid_length": 36, "vision_feature_dim": 192, "face_blendshape_valid_length": 36, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 215, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.971, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__17.npz", "feature_file_bytes": 84195, "feature_file_sha256": "e9c10667126703b2502a15198913c10e2cca2b6165dd4eeb4a8d99133a07e61f"}
|
||||
{"sample_id": "-egA8-b7-3M/18", "video_id": "-egA8-b7-3M", "clip_id": "18", "text": "It becomes easier at each one of these conferences to connect with people that you've met or that you're doing business with.", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/18.mp4", "duration_s": 8.386003, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 822, "audio_valid_length": 822, "audio_feature_dim": 25, "vision_raw_length": 42, "vision_valid_length": 42, "vision_feature_dim": 192, "face_blendshape_valid_length": 42, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 250, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.02, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__18.npz", "feature_file_bytes": 103490, "feature_file_sha256": "ab6ced6fc989adcc5af794eeb33d3d9320dd3399ab87630c7a108449caf64892"}
|
||||
{"sample_id": "-egA8-b7-3M/16", "video_id": "-egA8-b7-3M", "clip_id": "16", "text": "Third, another big benefit of exhibiting is connecting with existing clients.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/16.mp4", "duration_s": 5.538021, "ctc_inference_succeeded": true, "word_count": 11, "word_alignment_valid_count": 11, "audio_raw_length": 544, "audio_valid_length": 544, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 28, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 166, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.889, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__16.npz", "feature_file_bytes": 64870, "feature_file_sha256": "5d039a566cc9534f923e685e5577b09d0f8ac85b5c3c141df8831911c7744ef8"}
|
||||
{"sample_id": "-egA8-b7-3M/13", "video_id": "-egA8-b7-3M", "clip_id": "13", "text": "What are you doing that's different?\" They always want an answer.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/13.mp4", "duration_s": 4.183984, "ctc_inference_succeeded": true, "word_count": 11, "word_alignment_valid_count": 11, "audio_raw_length": 398, "audio_valid_length": 398, "audio_feature_dim": 25, "vision_raw_length": 21, "vision_valid_length": 21, "vision_feature_dim": 192, "face_blendshape_valid_length": 21, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 123, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.84, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__13.npz", "feature_file_bytes": 55221, "feature_file_sha256": "61e3a28eeb71434c2beb25c37bee7edace80c8cad9939c873a137d574cd9d8a0"}
|
||||
{"sample_id": "-egA8-b7-3M/1", "video_id": "-egA8-b7-3M", "clip_id": "1", "text": "I started a successful Legal Nurse Consulting Business in 1989. I mentor nurses who want to become Legal Nurse Consultants.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/1.mp4", "duration_s": 10.266016, "ctc_inference_succeeded": true, "word_count": 20, "word_alignment_valid_count": 19, "audio_raw_length": 1011, "audio_valid_length": 1011, "audio_feature_dim": 25, "vision_raw_length": 51, "vision_valid_length": 51, "vision_feature_dim": 192, "face_blendshape_valid_length": 51, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 306, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 1.115, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__1.npz", "feature_file_bytes": 112851, "feature_file_sha256": "f9f9240885fdb8109abbd3fae1e1628a0881744eb12fa019b2586ee68835898e"}
|
||||
{"sample_id": "-egA8-b7-3M/6", "video_id": "-egA8-b7-3M", "clip_id": "6", "text": "First exhibiting is a wonderful opportunity to network with other legal vendors.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/6.mp4", "duration_s": 6.264974, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 614, "audio_valid_length": 614, "audio_feature_dim": 25, "vision_raw_length": 32, "vision_valid_length": 32, "vision_feature_dim": 192, "face_blendshape_valid_length": 32, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 187, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.9, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__6.npz", "feature_file_bytes": 71552, "feature_file_sha256": "63ed3ef14c5d6bcaf97b9d5e69d5614d7e880b90f3ee7cf13245f546d15a7828"}
|
||||
{"sample_id": "-egA8-b7-3M/9", "video_id": "-egA8-b7-3M", "clip_id": "9", "text": "Secondly, another goal of exhibiting is building your company image.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/9.mp4", "duration_s": 5.089974, "ctc_inference_succeeded": true, "word_count": 10, "word_alignment_valid_count": 10, "audio_raw_length": 489, "audio_valid_length": 489, "audio_feature_dim": 25, "vision_raw_length": 25, "vision_valid_length": 25, "vision_feature_dim": 192, "face_blendshape_valid_length": 25, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 150, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.868, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__9.npz", "feature_file_bytes": 59194, "feature_file_sha256": "f20f151fe4322b86d3c9f6140972ac67c73aa32922b9eb4dbe0fbdf636065337"}
|
||||
{"sample_id": "-egA8-b7-3M/20", "video_id": "-egA8-b7-3M", "clip_id": "20", "text": "Now you've got a face that you can connect with a voice, and that makes you closer to that client.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-egA8-b7-3M/20.mp4", "duration_s": 6.644987, "ctc_inference_succeeded": true, "word_count": 20, "word_alignment_valid_count": 20, "audio_raw_length": 643, "audio_valid_length": 643, "audio_feature_dim": 25, "vision_raw_length": 33, "vision_valid_length": 33, "vision_feature_dim": 192, "face_blendshape_valid_length": 33, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 196, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.95, "feature_file": "outputs/q1_features/features/-egA8-b7-3M__20.npz", "feature_file_bytes": 87987, "feature_file_sha256": "f8d76619a0fc76832079ca699a9c5de1fe9cfc91ee4a2cafdbf366fa5ffeec8a"}
|
||||
{"sample_id": "-iRBcNs9oI8/3", "video_id": "-iRBcNs9oI8", "clip_id": "3", "text": "Well, it is the secret of power pose", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-iRBcNs9oI8/3.mp4", "duration_s": 5.621, "ctc_inference_succeeded": true, "word_count": 8, "word_alignment_valid_count": 8, "audio_raw_length": 549, "audio_valid_length": 549, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 167, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.918, "feature_file": "outputs/q1_features/features/-iRBcNs9oI8__3.npz", "feature_file_bytes": 55728, "feature_file_sha256": "68078a6892f9de5182b9d3ddc812137b46bae3bd1087336dcae6b764fe44881c"}
|
||||
{"sample_id": "-iRBcNs9oI8/7", "video_id": "-iRBcNs9oI8", "clip_id": "7", "text": "Well, for starters, let's look at the word \"power\"", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-iRBcNs9oI8/7.mp4", "duration_s": 4.104, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 396, "audio_valid_length": 396, "audio_feature_dim": 25, "vision_raw_length": 20, "vision_valid_length": 20, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 120, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.811, "feature_file": "outputs/q1_features/features/-iRBcNs9oI8__7.npz", "feature_file_bytes": 48402, "feature_file_sha256": "4041ad453cb24121d0fafda45cfff9dbbce57bdec40a825354376d5aecbc061c"}
|
||||
{"sample_id": "-iRBcNs9oI8/6", "video_id": "-iRBcNs9oI8", "clip_id": "6", "text": "What is a power pose", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-iRBcNs9oI8/6.mp4", "duration_s": 2.903, "ctc_inference_succeeded": true, "word_count": 5, "word_alignment_valid_count": 5, "audio_raw_length": 278, "audio_valid_length": 278, "audio_feature_dim": 25, "vision_raw_length": 15, "vision_valid_length": 15, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 85, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.767, "feature_file": "outputs/q1_features/features/-iRBcNs9oI8__6.npz", "feature_file_bytes": 34247, "feature_file_sha256": "33660b05c1f8be7f1f7b89b2400341df488b77a7695990462113cc919a703e0b"}
|
||||
{"sample_id": "-iRBcNs9oI8/9", "video_id": "-iRBcNs9oI8", "clip_id": "9", "text": "Power is similar to strength", "label": 1.3333333730697632, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-iRBcNs9oI8/9.mp4", "duration_s": 3.416, "ctc_inference_succeeded": true, "word_count": 5, "word_alignment_valid_count": 5, "audio_raw_length": 333, "audio_valid_length": 333, "audio_feature_dim": 25, "vision_raw_length": 17, "vision_valid_length": 17, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 102, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.816, "feature_file": "outputs/q1_features/features/-iRBcNs9oI8__9.npz", "feature_file_bytes": 36025, "feature_file_sha256": "5c234d0aae9de546fe807ff1f2f0c3e230d6786adbfc62571fcab8232dd4984e"}
|
||||
{"sample_id": "-iRBcNs9oI8/8", "video_id": "-iRBcNs9oI8", "clip_id": "8", "text": "I've drawn this man here, and if you can tell, he has a lot of big muscles, he looks very strong", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-iRBcNs9oI8/8.mp4", "duration_s": 8.093, "ctc_inference_succeeded": true, "word_count": 21, "word_alignment_valid_count": 21, "audio_raw_length": 798, "audio_valid_length": 798, "audio_feature_dim": 25, "vision_raw_length": 41, "vision_valid_length": 41, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 241, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.996, "feature_file": "outputs/q1_features/features/-iRBcNs9oI8__8.npz", "feature_file_bytes": 94217, "feature_file_sha256": "b11ac96118bcabbbc4c65f82a7d3c0cf44e8750ab856da822c865b9d8561caa0"}
|
||||
{"sample_id": "-lzEya4AM_4/5", "video_id": "-lzEya4AM_4", "clip_id": "5", "text": "If it falls into oh any of those three categories, inducing nausea and vomiting would be your next step.", "label": -0.6666666865348816, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-lzEya4AM_4/5.mp4", "duration_s": 7.675, "ctc_inference_succeeded": true, "word_count": 19, "word_alignment_valid_count": 19, "audio_raw_length": 752, "audio_valid_length": 752, "audio_feature_dim": 25, "vision_raw_length": 39, "vision_valid_length": 39, "vision_feature_dim": 192, "face_blendshape_valid_length": 39, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 229, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.054, "feature_file": "outputs/q1_features/features/-lzEya4AM_4__5.npz", "feature_file_bytes": 92703, "feature_file_sha256": "17c139126d6862765aecdc4b5c8fa8a3b9cce667ea9f1b450004aefb14c8c4a5"}
|
||||
{"sample_id": "-lzEya4AM_4/6", "video_id": "-lzEya4AM_4", "clip_id": "6", "text": "If the product or poison is some type of petroleum product or corrosive product, you would not attempt to induce vomiting and nausea, as as the product burned on the way down it could cause damage and burning on the way back up.", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-lzEya4AM_4/6.mp4", "duration_s": 14.791992, "ctc_inference_succeeded": true, "word_count": 43, "word_alignment_valid_count": 43, "audio_raw_length": 1470, "audio_valid_length": 1470, "audio_feature_dim": 25, "vision_raw_length": 74, "vision_valid_length": 74, "vision_feature_dim": 192, "face_blendshape_valid_length": 74, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 443, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.401, "feature_file": "outputs/q1_features/features/-lzEya4AM_4__6.npz", "feature_file_bytes": 184072, "feature_file_sha256": "ea3d7a1cf953b467441a8c8f69585457ca0d64ae2ac642aaa8ef5638d575ea3a"}
|
||||
{"sample_id": "-mJ2ud6oKI8/1", "video_id": "-mJ2ud6oKI8", "clip_id": "1", "text": "There are a dozen or more hands on techniques that we can do", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mJ2ud6oKI8/1.mp4", "duration_s": 6.103, "ctc_inference_succeeded": true, "word_count": 13, "word_alignment_valid_count": 13, "audio_raw_length": 601, "audio_valid_length": 601, "audio_feature_dim": 25, "vision_raw_length": 31, "vision_valid_length": 31, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 182, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.909, "feature_file": "outputs/q1_features/features/-mJ2ud6oKI8__1.npz", "feature_file_bytes": 42496, "feature_file_sha256": "cef94a67ec6c902c28ada0176e70c3c9dda548237dfc89adfbb1a49e58d63448"}
|
||||
{"sample_id": "-mJ2ud6oKI8/2", "video_id": "-mJ2ud6oKI8", "clip_id": "2", "text": "So physical therapists and chiropractors will do joint manipulations and mobilizations", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mJ2ud6oKI8/2.mp4", "duration_s": 5.731, "ctc_inference_succeeded": true, "word_count": 11, "word_alignment_valid_count": 11, "audio_raw_length": 566, "audio_valid_length": 566, "audio_feature_dim": 25, "vision_raw_length": 29, "vision_valid_length": 29, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 171, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.879, "feature_file": "outputs/q1_features/features/-mJ2ud6oKI8__2.npz", "feature_file_bytes": 38780, "feature_file_sha256": "7a75079ee9256bde17ba18fb45213ebdbfc73db7360cc228624f6acc55b3d12f"}
|
||||
{"sample_id": "-mJ2ud6oKI8/6", "video_id": "-mJ2ud6oKI8", "clip_id": "6", "text": "They are all very safe", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mJ2ud6oKI8/6.mp4", "duration_s": 2.257, "ctc_inference_succeeded": true, "word_count": 5, "word_alignment_valid_count": 5, "audio_raw_length": 218, "audio_valid_length": 218, "audio_feature_dim": 25, "vision_raw_length": 12, "vision_valid_length": 12, "vision_feature_dim": 192, "face_blendshape_valid_length": 12, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 67, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.751, "feature_file": "outputs/q1_features/features/-mJ2ud6oKI8__6.npz", "feature_file_bytes": 31649, "feature_file_sha256": "f50ed376f03cd8f4613014f78e16f0a6ec95f4c2657af6880ff0e8a946435cee"}
|
||||
{"sample_id": "-mJ2ud6oKI8/9", "video_id": "-mJ2ud6oKI8", "clip_id": "9", "text": "It's safe and the person will feel better later on, but it's sort of like flossing your teeth for the first time", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mJ2ud6oKI8/9.mp4", "duration_s": 7.033, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 686, "audio_valid_length": 686, "audio_feature_dim": 25, "vision_raw_length": 35, "vision_valid_length": 35, "vision_feature_dim": 192, "face_blendshape_valid_length": 34, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 208, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.133, "feature_file": "outputs/q1_features/features/-mJ2ud6oKI8__9.npz", "feature_file_bytes": 91413, "feature_file_sha256": "66e7fd67aced87b8cc140c15e29fc3acc4531965aa8347d529e3a13531d9ea61"}
|
||||
{"sample_id": "-mJ2ud6oKI8/8", "video_id": "-mJ2ud6oKI8", "clip_id": "8", "text": "Sometimes we have to stretch that joint that is already irritated", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mJ2ud6oKI8/8.mp4", "duration_s": 4.192, "ctc_inference_succeeded": true, "word_count": 11, "word_alignment_valid_count": 11, "audio_raw_length": 413, "audio_valid_length": 413, "audio_feature_dim": 25, "vision_raw_length": 21, "vision_valid_length": 21, "vision_feature_dim": 192, "face_blendshape_valid_length": 21, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 125, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.915, "feature_file": "outputs/q1_features/features/-mJ2ud6oKI8__8.npz", "feature_file_bytes": 55199, "feature_file_sha256": "2605a8ef0e9b58c906d4322f462b1b7546c7a862c849c765279e8f5df689f7f3"}
|
||||
{"sample_id": "-mqbVkbCndg/0", "video_id": "-mqbVkbCndg", "clip_id": "0", "text": "How, at a particular moment in time—our moment in time—are they limited", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-mqbVkbCndg/0.mp4", "duration_s": 6.466667, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 634, "audio_valid_length": 634, "audio_feature_dim": 25, "vision_raw_length": 33, "vision_valid_length": 33, "vision_feature_dim": 192, "face_blendshape_valid_length": 33, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 194, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.108, "feature_file": "outputs/q1_features/features/-mqbVkbCndg__0.npz", "feature_file_bytes": 72269, "feature_file_sha256": "b7d742a9161423cb1db8af233308b75552060cdae423464bcec4e288c2e91f2f"}
|
||||
{"sample_id": "-t217m2on-s/2", "video_id": "-t217m2on-s", "clip_id": "2", "text": "But a good thing to do is yawning, chewing gum is effective.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-t217m2on-s/2.mp4", "duration_s": 5.686003, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 559, "audio_valid_length": 559, "audio_feature_dim": 25, "vision_raw_length": 29, "vision_valid_length": 29, "vision_feature_dim": 192, "face_blendshape_valid_length": 29, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 170, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.873, "feature_file": "outputs/q1_features/features/-t217m2on-s__2.npz", "feature_file_bytes": 67378, "feature_file_sha256": "8bc2165c2e59ba4ad6bc7c754121d6e000ea808902f33894ffc011e8de04184b"}
|
||||
{"sample_id": "-t217m2on-s/7", "video_id": "-t217m2on-s", "clip_id": "7", "text": "If you find that your ears consistently do this and you can't pop them often, you'll definitely need to see a physician regarding those things, it could be something more of a nasal infection or a sinus infection that he would need to deal with.", "label": -0.6666666865348816, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-t217m2on-s/7.mp4", "duration_s": 17.183008, "ctc_inference_succeeded": true, "word_count": 45, "word_alignment_valid_count": 45, "audio_raw_length": 1698, "audio_valid_length": 1698, "audio_feature_dim": 25, "vision_raw_length": 86, "vision_valid_length": 86, "vision_feature_dim": 192, "face_blendshape_valid_length": 86, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 512, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.401, "feature_file": "outputs/q1_features/features/-t217m2on-s__7.npz", "feature_file_bytes": 203231, "feature_file_sha256": "2f46e5ccaab773f47dc3c868fb4ebee655be8c1e63417a929e404634497e9145"}
|
||||
{"sample_id": "-tANM6ETl_M/3", "video_id": "-tANM6ETl_M", "clip_id": "3", "text": "The first place is either you have a prospect, or a customer who's never done it before, or they've never tried it.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tANM6ETl_M/3.mp4", "duration_s": 6.758008, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 656, "audio_valid_length": 656, "audio_feature_dim": 25, "vision_raw_length": 34, "vision_valid_length": 34, "vision_feature_dim": 192, "face_blendshape_valid_length": 34, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 200, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.372, "feature_file": "outputs/q1_features/features/-tANM6ETl_M__3.npz", "feature_file_bytes": 93347, "feature_file_sha256": "f02e592e9523d42da4cb803c1b88b36aae284afd0a69a24e1b9e687888142b37"}
|
||||
{"sample_id": "-tPCytz4rww/11", "video_id": "-tPCytz4rww", "clip_id": "11", "text": "Make sure that your using comps that are not larger, no larger than twelve hundred square feet.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tPCytz4rww/11.mp4", "duration_s": 5.466992, "ctc_inference_succeeded": true, "word_count": 17, "word_alignment_valid_count": 17, "audio_raw_length": 533, "audio_valid_length": 533, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 28, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 164, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.852, "feature_file": "outputs/q1_features/features/-tPCytz4rww__11.npz", "feature_file_bytes": 76420, "feature_file_sha256": "5bcbfe9dd695b89b7da60668a4cc5ce80373e327c87b45a1651259db54661224"}
|
||||
{"sample_id": "-tPCytz4rww/10", "video_id": "-tPCytz4rww", "clip_id": "10", "text": "Say twenty percent so if you've got a thousand square foot condo.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tPCytz4rww/10.mp4", "duration_s": 4.788997, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 463, "audio_valid_length": 463, "audio_feature_dim": 25, "vision_raw_length": 24, "vision_valid_length": 24, "vision_feature_dim": 192, "face_blendshape_valid_length": 24, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 142, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.875, "feature_file": "outputs/q1_features/features/-tPCytz4rww__10.npz", "feature_file_bytes": 60662, "feature_file_sha256": "d2934c2150ce2e1e0062bf3044d9d7af3786db03cbf35a7c823d7d8354de6365"}
|
||||
{"sample_id": "-tPCytz4rww/12", "video_id": "-tPCytz4rww", "clip_id": "12", "text": "No less than eight hundred squire feet and going to similar in, similar with bedrooms and bathrooms as well and hopefully the complexes have similar amenities.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tPCytz4rww/12.mp4", "duration_s": 11.863997, "ctc_inference_succeeded": true, "word_count": 26, "word_alignment_valid_count": 26, "audio_raw_length": 1169, "audio_valid_length": 1169, "audio_feature_dim": 25, "vision_raw_length": 59, "vision_valid_length": 59, "vision_feature_dim": 192, "face_blendshape_valid_length": 59, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 353, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.156, "feature_file": "outputs/q1_features/features/-tPCytz4rww__12.npz", "feature_file_bytes": 133451, "feature_file_sha256": "a6ff71df17d7bc392bfc52445b482401e0a995fe230868730823dea3a044f073"}
|
||||
{"sample_id": "-tPCytz4rww/16", "video_id": "-tPCytz4rww", "clip_id": "16", "text": "So make sure to get a through or to do a through cleaning of the property.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tPCytz4rww/16.mp4", "duration_s": 7.20599, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 709, "audio_valid_length": 709, "audio_feature_dim": 25, "vision_raw_length": 36, "vision_valid_length": 36, "vision_feature_dim": 192, "face_blendshape_valid_length": 36, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 216, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.933, "feature_file": "outputs/q1_features/features/-tPCytz4rww__16.npz", "feature_file_bytes": 83725, "feature_file_sha256": "6934aa9c66e7aa464a0a281e47e1220e87d5beadd74e00f287f8f088946bc21c"}
|
||||
{"sample_id": "-tPCytz4rww/18", "video_id": "-tPCytz4rww", "clip_id": "18", "text": "Do so and as well you'll also want to remove any clutter from that you've accumulated.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-tPCytz4rww/18.mp4", "duration_s": 6.644987, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 652, "audio_valid_length": 652, "audio_feature_dim": 25, "vision_raw_length": 34, "vision_valid_length": 34, "vision_feature_dim": 192, "face_blendshape_valid_length": 34, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 199, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.92, "feature_file": "outputs/q1_features/features/-tPCytz4rww__18.npz", "feature_file_bytes": 81628, "feature_file_sha256": "9df4418cac050f4385f8decdb1d71025504d9c8d01ccd62c177c8400651de10d"}
|
||||
{"sample_id": "-vxjVxOeScU/4", "video_id": "-vxjVxOeScU", "clip_id": "4", "text": "You're going to talk about their life, their marriage and usually how amazing it is that they've stayed together this long.", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-vxjVxOeScU/4.mp4", "duration_s": 9.127018, "ctc_inference_succeeded": true, "word_count": 21, "word_alignment_valid_count": 21, "audio_raw_length": 899, "audio_valid_length": 899, "audio_feature_dim": 25, "vision_raw_length": 46, "vision_valid_length": 46, "vision_feature_dim": 192, "face_blendshape_valid_length": 46, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 272, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.022, "feature_file": "outputs/q1_features/features/-vxjVxOeScU__4.npz", "feature_file_bytes": 109211, "feature_file_sha256": "f3d2da4c79b194cb5d88c9a25e5798718b0a54a4ebaa03859d1dfe8cf44c0e3e"}
|
||||
{"sample_id": "-wMB_hJL-3o/7", "video_id": "-wMB_hJL-3o", "clip_id": "7", "text": "So if you have a loved one who is depressed those are some of the things that you should think about doing.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wMB_hJL-3o/7.mp4", "duration_s": 6.04401, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 593, "audio_valid_length": 593, "audio_feature_dim": 25, "vision_raw_length": 31, "vision_valid_length": 31, "vision_feature_dim": 192, "face_blendshape_valid_length": 31, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 181, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.862, "feature_file": "outputs/q1_features/features/-wMB_hJL-3o__7.npz", "feature_file_bytes": 87786, "feature_file_sha256": "abc6004b9c9b862a710ef51a7add4b0e15e9decd398568ba5c5c78097b9601e5"}
|
||||
{"sample_id": "-wny0OAz3g8/1", "video_id": "-wny0OAz3g8", "clip_id": "1", "text": "And because they couldn’t join unions, many Black workers couldn’t get manufacturing or trade work – which paid much better than service work", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/1.mp4", "duration_s": 6.84401, "ctc_inference_succeeded": true, "word_count": 23, "word_alignment_valid_count": 22, "audio_raw_length": 673, "audio_valid_length": 673, "audio_feature_dim": 25, "vision_raw_length": 35, "vision_valid_length": 35, "vision_feature_dim": 192, "face_blendshape_valid_length": 14, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 205, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 1.079, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__1.npz", "feature_file_bytes": 94004, "feature_file_sha256": "362a4d42cba56aa7e531eef1357a32499f8c65e21145586d32ed7947d1acda76"}
|
||||
{"sample_id": "-wny0OAz3g8/0", "video_id": "-wny0OAz3g8", "clip_id": "0", "text": "trade labor unions didn’t allow Black workers to join", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/0.mp4", "duration_s": 3.333333, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 323, "audio_valid_length": 323, "audio_feature_dim": 25, "vision_raw_length": 17, "vision_valid_length": 17, "vision_feature_dim": 192, "face_blendshape_valid_length": 14, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 100, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.855, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__0.npz", "feature_file_bytes": 46886, "feature_file_sha256": "fe0f40f6343ea3cff917f5145e9f0fe9dee535578478742de40028d28050d7b7"}
|
||||
{"sample_id": "-wny0OAz3g8/3", "video_id": "-wny0OAz3g8", "clip_id": "3", "text": "Which then allowed the white workers and unions to justify their decision to not allow black workers into their union", "label": -1.3333333730697632, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/3.mp4", "duration_s": 6.146029, "ctc_inference_succeeded": true, "word_count": 20, "word_alignment_valid_count": 20, "audio_raw_length": 605, "audio_valid_length": 605, "audio_feature_dim": 25, "vision_raw_length": 31, "vision_valid_length": 31, "vision_feature_dim": 192, "face_blendshape_valid_length": 8, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 184, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.039, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__3.npz", "feature_file_bytes": 84176, "feature_file_sha256": "cda92d90e4e5444e961776b9f99f24af0e2155fa91717f2c7abb4c00f2971364"}
|
||||
{"sample_id": "-wny0OAz3g8/2", "video_id": "-wny0OAz3g8", "clip_id": "2", "text": "And because they couldn’t get these jobs, Black communities had more men out of work, higher rates of poverty, and more criminal behavior", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/2.mp4", "duration_s": 6.686979, "ctc_inference_succeeded": true, "word_count": 23, "word_alignment_valid_count": 23, "audio_raw_length": 648, "audio_valid_length": 648, "audio_feature_dim": 25, "vision_raw_length": 33, "vision_valid_length": 33, "vision_feature_dim": 192, "face_blendshape_valid_length": 27, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 197, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.066, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__2.npz", "feature_file_bytes": 89372, "feature_file_sha256": "6e4783cfaf56697e1dab151f62b937b00c7ae88edbab3686766ab35f615a765d"}
|
||||
{"sample_id": "-wny0OAz3g8/5", "video_id": "-wny0OAz3g8", "clip_id": "5", "text": "This is what’s now known as racial formation theory, a theory formalized by modern sociologists Michael Omi and Howard Winant", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/5.mp4", "duration_s": 6.911979, "ctc_inference_succeeded": true, "word_count": 20, "word_alignment_valid_count": 20, "audio_raw_length": 670, "audio_valid_length": 670, "audio_feature_dim": 25, "vision_raw_length": 34, "vision_valid_length": 34, "vision_feature_dim": 192, "face_blendshape_valid_length": 6, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 204, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.996, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__5.npz", "feature_file_bytes": 86434, "feature_file_sha256": "d8b108c0c2a9e614329ac44f31bf77ecdeb69490c601851f298c0c9622aa2e8f"}
|
||||
{"sample_id": "-wny0OAz3g8/7", "video_id": "-wny0OAz3g8", "clip_id": "7", "text": "Omi and Winant argue that the concept of race came about as a tool to justify and maintain the economic and political power held by those of European descent", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/7.mp4", "duration_s": 8.067969, "ctc_inference_succeeded": true, "word_count": 29, "word_alignment_valid_count": 29, "audio_raw_length": 787, "audio_valid_length": 787, "audio_feature_dim": 25, "vision_raw_length": 40, "vision_valid_length": 40, "vision_feature_dim": 192, "face_blendshape_valid_length": 35, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 240, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.123, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__7.npz", "feature_file_bytes": 115720, "feature_file_sha256": "82baf4e55ebd2068717dd4a15fecd24a1f34843aa5c7f888a5405666570e6a9d"}
|
||||
{"sample_id": "-wny0OAz3g8/9", "video_id": "-wny0OAz3g8", "clip_id": "9", "text": "He explores why Black and White Americans tend to have such different outcomes in terms of income, education, and more", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-wny0OAz3g8/9.mp4", "duration_s": 6.213021, "ctc_inference_succeeded": true, "word_count": 20, "word_alignment_valid_count": 20, "audio_raw_length": 600, "audio_valid_length": 600, "audio_feature_dim": 25, "vision_raw_length": 31, "vision_valid_length": 31, "vision_feature_dim": 192, "face_blendshape_valid_length": 29, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 183, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.023, "feature_file": "outputs/q1_features/features/-wny0OAz3g8__9.npz", "feature_file_bytes": 86748, "feature_file_sha256": "a5e965ff931d5a3d9872095ddb7bb48c65e2596de9a73b345d5e493e4b5aa449"}
|
||||
{"sample_id": "-571d8cVauQ/0", "video_id": "-571d8cVauQ", "clip_id": "0", "text": "This is Rhett Reiger, White Caspian Studios on behalf of Expert Village.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-571d8cVauQ/0.mp4", "duration_s": 5.066667, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 495, "audio_valid_length": 495, "audio_feature_dim": 25, "vision_raw_length": 26, "vision_valid_length": 26, "vision_feature_dim": 192, "face_blendshape_valid_length": 25, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 152, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.815, "feature_file": "outputs/q1_features/features/-571d8cVauQ__0.npz", "feature_file_bytes": 58874, "feature_file_sha256": "f7619fd9f48c31307f3ea25e78bf820a505057521f2f155d75f80b9933dce7ea"}
|
||||
{"sample_id": "-571d8cVauQ/5", "video_id": "-571d8cVauQ", "clip_id": "5", "text": "So very important to go out to the locations, walk around, talk with the owners if you can, tell them what you're doing, build a little excitement, put a little glitz on there and let everybody knows this is a very valuable spot.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-571d8cVauQ/5.mp4", "duration_s": 15.272982, "ctc_inference_succeeded": true, "word_count": 43, "word_alignment_valid_count": 43, "audio_raw_length": 1507, "audio_valid_length": 1507, "audio_feature_dim": 25, "vision_raw_length": 76, "vision_valid_length": 76, "vision_feature_dim": 192, "face_blendshape_valid_length": 76, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 455, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.308, "feature_file": "outputs/q1_features/features/-571d8cVauQ__5.npz", "feature_file_bytes": 186922, "feature_file_sha256": "268d96a63185239a759a6ea3a1807abd37d138b95400ef4cb970125cba68e259"}
|
||||
{"sample_id": "-I_e4mIh0yE/1", "video_id": "-I_e4mIh0yE", "clip_id": "1", "text": "In the United States we don't punish failure to the degree to which failure is punished in Europe.", "label": -0.6666666865348816, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-I_e4mIh0yE/1.mp4", "duration_s": 7.622005, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 740, "audio_valid_length": 740, "audio_feature_dim": 25, "vision_raw_length": 38, "vision_valid_length": 38, "vision_feature_dim": 192, "face_blendshape_valid_length": 38, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 225, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.933, "feature_file": "outputs/q1_features/features/-I_e4mIh0yE__1.npz", "feature_file_bytes": 89671, "feature_file_sha256": "fd45f8d3be6a030b902719e09b8d0e39b198a3897e06a952a7ac73bd596d0102"}
|
||||
{"sample_id": "-I_e4mIh0yE/3", "video_id": "-I_e4mIh0yE", "clip_id": "3", "text": "It's perceived that you have actually learned something, over the course of your carreer, and that you won't make the mistake twice.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-I_e4mIh0yE/3.mp4", "duration_s": 9.163021, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 895, "audio_valid_length": 895, "audio_feature_dim": 25, "vision_raw_length": 46, "vision_valid_length": 46, "vision_feature_dim": 192, "face_blendshape_valid_length": 46, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 271, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.06, "feature_file": "outputs/q1_features/features/-I_e4mIh0yE__3.npz", "feature_file_bytes": 106161, "feature_file_sha256": "5bc0a18e3a0f0bca0dc14f2a2ce3293c3ce6fa996e51c7a1aaed69c3c4b78dc1"}
|
||||
{"sample_id": "-UacrmKiTn4/10", "video_id": "-UacrmKiTn4", "clip_id": "10", "text": "Because, if they are not in any way held accountable for reading the material they won't do it.", "label": -0.6666666865348816, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UacrmKiTn4/10.mp4", "duration_s": 7.361979, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 720, "audio_valid_length": 720, "audio_feature_dim": 25, "vision_raw_length": 37, "vision_valid_length": 37, "vision_feature_dim": 192, "face_blendshape_valid_length": 37, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 218, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.936, "feature_file": "outputs/q1_features/features/-UacrmKiTn4__10.npz", "feature_file_bytes": 90141, "feature_file_sha256": "d83feb6007b70660e1a8bd9d92f144ee2ff1226d9dd7cacebf723fd2010474f5"}
|
||||
{"sample_id": "-UacrmKiTn4/4", "video_id": "-UacrmKiTn4", "clip_id": "4", "text": "Just given to their own devices they are not going to read the textbook.", "label": -1.3333333730697632, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UacrmKiTn4/4.mp4", "duration_s": 4.741016, "ctc_inference_succeeded": true, "word_count": 14, "word_alignment_valid_count": 14, "audio_raw_length": 464, "audio_valid_length": 464, "audio_feature_dim": 25, "vision_raw_length": 24, "vision_valid_length": 24, "vision_feature_dim": 192, "face_blendshape_valid_length": 24, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 142, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.798, "feature_file": "outputs/q1_features/features/-UacrmKiTn4__4.npz", "feature_file_bytes": 64832, "feature_file_sha256": "0ad3024c7377b55b9477f09cf8e74b30f627abf1a2b6ef0a4b1fc418e5fb07ff"}
|
||||
{"sample_id": "-hnBHBN8p5A/7", "video_id": "-hnBHBN8p5A", "clip_id": "7", "text": "Picture this, before we actually start hacking, we’re in a room formal setting", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-hnBHBN8p5A/7.mp4", "duration_s": 7.372, "ctc_inference_succeeded": true, "word_count": 13, "word_alignment_valid_count": 13, "audio_raw_length": 726, "audio_valid_length": 726, "audio_feature_dim": 25, "vision_raw_length": 36, "vision_valid_length": 36, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 176, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.971, "feature_file": "outputs/q1_features/features/-hnBHBN8p5A__7.npz", "feature_file_bytes": 72066, "feature_file_sha256": "727738b5db20f39e7202422ae7b6aae13a7beaed73032dd4bf9d1b4f31a3b6cd"}
|
||||
{"sample_id": "-hnBHBN8p5A/6", "video_id": "-hnBHBN8p5A", "clip_id": "6", "text": "Discussion, how to discuss ideas and opinions more effectively than a native speaker", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-hnBHBN8p5A/6.mp4", "duration_s": 6.401, "ctc_inference_succeeded": true, "word_count": 13, "word_alignment_valid_count": 13, "audio_raw_length": 629, "audio_valid_length": 629, "audio_feature_dim": 25, "vision_raw_length": 31, "vision_valid_length": 31, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 153, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.95, "feature_file": "outputs/q1_features/features/-hnBHBN8p5A__6.npz", "feature_file_bytes": 65954, "feature_file_sha256": "62feca3ba0ca057a7b7b1b4b8c760b577480a55c3d1307a5e32d491d794fda36"}
|
||||
{"sample_id": "-qDkUB0GgYY/6", "video_id": "-qDkUB0GgYY", "clip_id": "6", "text": "We always love to hear what you say, and like and share this video as well.", "label": 1.3333333730697632, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-qDkUB0GgYY/6.mp4", "duration_s": 4.677995, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 457, "audio_valid_length": 457, "audio_feature_dim": 25, "vision_raw_length": 24, "vision_valid_length": 24, "vision_feature_dim": 192, "face_blendshape_valid_length": 24, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 140, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.816, "feature_file": "outputs/q1_features/features/-qDkUB0GgYY__6.npz", "feature_file_bytes": 69147, "feature_file_sha256": "7a23449abba588d30c3ba564016c2b28c80245bc918bc5325851be1c125fdf7e"}
|
||||
{"sample_id": "-uywlfIYOS8/4", "video_id": "-uywlfIYOS8", "clip_id": "4", "text": "And then from a brand point of view, we need to make sure we're driving the relevant insight.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-uywlfIYOS8/4.mp4", "duration_s": 6.044987, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 584, "audio_valid_length": 584, "audio_feature_dim": 25, "vision_raw_length": 30, "vision_valid_length": 30, "vision_feature_dim": 192, "face_blendshape_valid_length": 30, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 179, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.873, "feature_file": "outputs/q1_features/features/-uywlfIYOS8__4.npz", "feature_file_bytes": 80911, "feature_file_sha256": "3d9ca40b5bf8a398539117a43a682eb077d3230c6adeba5bb70d605d47af3507"}
|
||||
{"sample_id": "-6rXp3zJ3kc/8", "video_id": "-6rXp3zJ3kc", "clip_id": "8", "text": "Many people are not until they get to be a older age and they realize that gosh they wasted a lot of time and money in placing bets on stock that's ultimately lost value.", "label": -1.0, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-6rXp3zJ3kc/8.mp4", "duration_s": 12.805013, "ctc_inference_succeeded": true, "word_count": 34, "word_alignment_valid_count": 34, "audio_raw_length": 1269, "audio_valid_length": 1269, "audio_feature_dim": 25, "vision_raw_length": 64, "vision_valid_length": 64, "vision_feature_dim": 192, "face_blendshape_valid_length": 64, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 384, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.243, "feature_file": "outputs/q1_features/features/-6rXp3zJ3kc__8.npz", "feature_file_bytes": 155936, "feature_file_sha256": "9154d8ce74a2c17c50738db3c0d947d2e71e68667935e7d95d3ae391d133531b"}
|
||||
{"sample_id": "-9y-fZ3swSY/0", "video_id": "-9y-fZ3swSY", "clip_id": "0", "text": "is, you can say, hey I really like baby skin, they are so soft, they don’t have any hair on their face", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-9y-fZ3swSY/0.mp4", "duration_s": 6.833333, "ctc_inference_succeeded": true, "word_count": 22, "word_alignment_valid_count": 22, "audio_raw_length": 671, "audio_valid_length": 671, "audio_feature_dim": 25, "vision_raw_length": 35, "vision_valid_length": 35, "vision_feature_dim": 192, "face_blendshape_valid_length": 35, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 205, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.083, "feature_file": "outputs/q1_features/features/-9y-fZ3swSY__0.npz", "feature_file_bytes": 95005, "feature_file_sha256": "3a2ed2dc4d08a11bcc35cfb68f6b83ac50c801f276c38f50b645ea6c0e9d5e4e"}
|
||||
{"sample_id": "-9y-fZ3swSY/4", "video_id": "-9y-fZ3swSY", "clip_id": "4", "text": "I’ve seen this in US or in the US", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-9y-fZ3swSY/4.mp4", "duration_s": 2.821029, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 262, "audio_valid_length": 262, "audio_feature_dim": 25, "vision_raw_length": 14, "vision_valid_length": 14, "vision_feature_dim": 192, "face_blendshape_valid_length": 13, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 81, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.796, "feature_file": "outputs/q1_features/features/-9y-fZ3swSY__4.npz", "feature_file_bytes": 39524, "feature_file_sha256": "97543a5bf15709d01d29423822918e8a42b0f20d562cf72f4a64d4ea6be88d0b"}
|
||||
{"sample_id": "-9y-fZ3swSY/8", "video_id": "-9y-fZ3swSY", "clip_id": "8", "text": "That’s a more decent and more polite way to call a lady", "label": 1.6666666269302368, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-9y-fZ3swSY/8.mp4", "duration_s": 4.988997, "ctc_inference_succeeded": true, "word_count": 12, "word_alignment_valid_count": 12, "audio_raw_length": 487, "audio_valid_length": 487, "audio_feature_dim": 25, "vision_raw_length": 25, "vision_valid_length": 25, "vision_feature_dim": 192, "face_blendshape_valid_length": 18, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 149, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.013, "feature_file": "outputs/q1_features/features/-9y-fZ3swSY__8.npz", "feature_file_bytes": 61536, "feature_file_sha256": "e3252b6b0b965fbd84d9435ed763b7b8c8c82557b6a82c93a06feb2a2e75c502"}
|
||||
{"sample_id": "-AUZQgSxyPQ/2", "video_id": "-AUZQgSxyPQ", "clip_id": "2", "text": "The perfect soul mate to the Clarisonic Spot Therapy Brush, this gentle, Ph balanced and hydrating exfoliant containing jojoba and acai fruit oils and bamboo and prickly bear extracts deliver intense healing, while smooth granules buff away dead, dry skin cells.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-AUZQgSxyPQ/2.mp4", "duration_s": 22.511003, "ctc_inference_succeeded": true, "word_count": 41, "word_alignment_valid_count": 41, "audio_raw_length": 2236, "audio_valid_length": 2236, "audio_feature_dim": 25, "vision_raw_length": 113, "vision_valid_length": 113, "vision_feature_dim": 192, "face_blendshape_valid_length": 113, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 674, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 2.075, "feature_file": "outputs/q1_features/features/-AUZQgSxyPQ__2.npz", "feature_file_bytes": 221014, "feature_file_sha256": "5d5302d19af9b0ca3cb9c85523bce5d3010dbaa8029b4f13064998f720952f3e"}
|
||||
{"sample_id": "-HeZS2-Prhc/2", "video_id": "-HeZS2-Prhc", "clip_id": "2", "text": "The August jobs report is out and it was seen overall as solid but not great.", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-HeZS2-Prhc/2.mp4", "duration_s": 8.261979, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 811, "audio_valid_length": 811, "audio_feature_dim": 25, "vision_raw_length": 41, "vision_valid_length": 41, "vision_feature_dim": 192, "face_blendshape_valid_length": 41, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 246, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.003, "feature_file": "outputs/q1_features/features/-HeZS2-Prhc__2.npz", "feature_file_bytes": 91019, "feature_file_sha256": "447eabf4ef50af858c6d189b5145a4c1f109157d0c5afa2f505201ca8d2c3f59"}
|
||||
{"sample_id": "-MeTTeMJBNc/0", "video_id": "-MeTTeMJBNc", "clip_id": "0", "text": "Okay, what happens at this point after we've taken this brief walk down memory lane, is the presentation of the gift.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-MeTTeMJBNc/0.mp4", "duration_s": 9.3, "ctc_inference_succeeded": true, "word_count": 21, "word_alignment_valid_count": 21, "audio_raw_length": 917, "audio_valid_length": 917, "audio_feature_dim": 25, "vision_raw_length": 47, "vision_valid_length": 47, "vision_feature_dim": 192, "face_blendshape_valid_length": 46, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 279, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.048, "feature_file": "outputs/q1_features/features/-MeTTeMJBNc__0.npz", "feature_file_bytes": 100330, "feature_file_sha256": "0fe362d119a5e1efdf6813913b63c513fef14c2fb496022a2a944a21a60cf930"}
|
||||
{"sample_id": "-MeTTeMJBNc/13", "video_id": "-MeTTeMJBNc", "clip_id": "13", "text": "It just needs to be a simple statement, and then you present the gift.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-MeTTeMJBNc/13.mp4", "duration_s": 5.430013, "ctc_inference_succeeded": true, "word_count": 14, "word_alignment_valid_count": 14, "audio_raw_length": 521, "audio_valid_length": 521, "audio_feature_dim": 25, "vision_raw_length": 27, "vision_valid_length": 27, "vision_feature_dim": 192, "face_blendshape_valid_length": 27, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 159, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.888, "feature_file": "outputs/q1_features/features/-MeTTeMJBNc__13.npz", "feature_file_bytes": 66667, "feature_file_sha256": "2707ebca0708b469cbe40988fef1a496dd58412d1fc2e0279abbab33daf11366"}
|
||||
{"sample_id": "-MeTTeMJBNc/7", "video_id": "-MeTTeMJBNc", "clip_id": "7", "text": "Maybe you could find a picture of the couple from their wedding or sometime in their life, or maybe even a current picture and have it put in a beautiful frame.", "label": 1.3333333730697632, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-MeTTeMJBNc/7.mp4", "duration_s": 10.516992, "ctc_inference_succeeded": true, "word_count": 31, "word_alignment_valid_count": 31, "audio_raw_length": 1037, "audio_valid_length": 1037, "audio_feature_dim": 25, "vision_raw_length": 53, "vision_valid_length": 53, "vision_feature_dim": 192, "face_blendshape_valid_length": 53, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 314, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.184, "feature_file": "outputs/q1_features/features/-MeTTeMJBNc__7.npz", "feature_file_bytes": 134532, "feature_file_sha256": "e8b7083df69bdf89ff2c931f6facab62f6d5a306b7f0b03ff09f8a1bc94e4100"}
|
||||
{"sample_id": "-RfYyzHpjk4/11", "video_id": "-RfYyzHpjk4", "clip_id": "11", "text": "So get your friends lined up, get your business colleagues lined up and have a good time.", "label": 2.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-RfYyzHpjk4/11.mp4", "duration_s": 5.238997, "ctc_inference_succeeded": true, "word_count": 17, "word_alignment_valid_count": 17, "audio_raw_length": 503, "audio_valid_length": 503, "audio_feature_dim": 25, "vision_raw_length": 26, "vision_valid_length": 26, "vision_feature_dim": 192, "face_blendshape_valid_length": 26, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 154, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.02, "feature_file": "outputs/q1_features/features/-RfYyzHpjk4__11.npz", "feature_file_bytes": 73768, "feature_file_sha256": "fca832f3b8e7ed259b6954939132ff2b2bdcb94259a25600f27a5b842fc1657d"}
|
||||
{"sample_id": "-RfYyzHpjk4/8", "video_id": "-RfYyzHpjk4", "clip_id": "8", "text": "It's pretty, pretty easy to do but you got to set up those numbers ahead of time.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-RfYyzHpjk4/8.mp4", "duration_s": 4.588997, "ctc_inference_succeeded": true, "word_count": 17, "word_alignment_valid_count": 17, "audio_raw_length": 449, "audio_valid_length": 449, "audio_feature_dim": 25, "vision_raw_length": 23, "vision_valid_length": 23, "vision_feature_dim": 192, "face_blendshape_valid_length": 23, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 137, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.994, "feature_file": "outputs/q1_features/features/-RfYyzHpjk4__8.npz", "feature_file_bytes": 69862, "feature_file_sha256": "ec1d60f3e703564535e1da5f3ecb56f4ad96de90ef791e36a1c1555eb80fdcb8"}
|
||||
{"sample_id": "-RfYyzHpjk4/2", "video_id": "-RfYyzHpjk4", "clip_id": "2", "text": "You can make a conference call but it takes quite a bit of planning, well not a lot of planning it's pretty easy to do.", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-RfYyzHpjk4/2.mp4", "duration_s": 5.516016, "ctc_inference_succeeded": true, "word_count": 25, "word_alignment_valid_count": 25, "audio_raw_length": 535, "audio_valid_length": 535, "audio_feature_dim": 25, "vision_raw_length": 28, "vision_valid_length": 28, "vision_feature_dim": 192, "face_blendshape_valid_length": 27, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 164, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.959, "feature_file": "outputs/q1_features/features/-RfYyzHpjk4__2.npz", "feature_file_bytes": 84993, "feature_file_sha256": "6b7191f85e0c3f7aabded124641d79a67eaf2ed1a784b2a4d13803900877654f"}
|
||||
{"sample_id": "-UUCSKoHeMA/0", "video_id": "-UUCSKoHeMA", "clip_id": "0", "text": "I mentioned a word in the last clip called 'monotone', and I want to talk about that briefly.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-UUCSKoHeMA/0.mp4", "duration_s": 7.8, "ctc_inference_succeeded": true, "word_count": 18, "word_alignment_valid_count": 18, "audio_raw_length": 769, "audio_valid_length": 769, "audio_feature_dim": 25, "vision_raw_length": 39, "vision_valid_length": 39, "vision_feature_dim": 192, "face_blendshape_valid_length": 38, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 234, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.975, "feature_file": "outputs/q1_features/features/-UUCSKoHeMA__0.npz", "feature_file_bytes": 86051, "feature_file_sha256": "6911fe030eef9b18344a66f661f78d8a4af466bab0c0182e44b0d7c86a1ddabc"}
|
||||
{"sample_id": "-ri04Z7vwnc/0", "video_id": "-ri04Z7vwnc", "clip_id": "0", "text": "going to get married or are already married", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-ri04Z7vwnc/0.mp4", "duration_s": 2.807, "ctc_inference_succeeded": true, "word_count": 8, "word_alignment_valid_count": 8, "audio_raw_length": 272, "audio_valid_length": 272, "audio_feature_dim": 25, "vision_raw_length": 14, "vision_valid_length": 14, "vision_feature_dim": 192, "face_blendshape_valid_length": 0, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 67, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["no_face_blendshapes_detected"], "processing_seconds": 0.745, "feature_file": "outputs/q1_features/features/-ri04Z7vwnc__0.npz", "feature_file_bytes": 39930, "feature_file_sha256": "5a29a9981d8fdee10e0de96b5389c9b8a4b81ee4536bac52f1410779498336b1"}
|
||||
{"sample_id": "-ri04Z7vwnc/2", "video_id": "-ri04Z7vwnc", "clip_id": "2", "text": "most people think it'll sort itself out, \"we'll discuss it later,\" it's not something too important", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-ri04Z7vwnc/2.mp4", "duration_s": 6.027, "ctc_inference_succeeded": true, "word_count": 16, "word_alignment_valid_count": 16, "audio_raw_length": 587, "audio_valid_length": 587, "audio_feature_dim": 25, "vision_raw_length": 29, "vision_valid_length": 29, "vision_feature_dim": 192, "face_blendshape_valid_length": 10, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 143, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.895, "feature_file": "outputs/q1_features/features/-ri04Z7vwnc__2.npz", "feature_file_bytes": 73850, "feature_file_sha256": "0994751df868803b7b6afbeed4dec9e66560e1ec140737613b4d9c92b2e34651"}
|
||||
{"sample_id": "-ri04Z7vwnc/5", "video_id": "-ri04Z7vwnc", "clip_id": "5", "text": "\" So I think it's important to discuss finances", "label": 0.3333333432674408, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-ri04Z7vwnc/5.mp4", "duration_s": 3.545, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 8, "audio_raw_length": 339, "audio_valid_length": 339, "audio_feature_dim": 25, "vision_raw_length": 17, "vision_valid_length": 17, "vision_feature_dim": 192, "face_blendshape_valid_length": 17, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 83, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 0.854, "feature_file": "outputs/q1_features/features/-ri04Z7vwnc__5.npz", "feature_file_bytes": 47804, "feature_file_sha256": "219e356124bc7ae293351c0410bf4415ce920daa7e773281273649044e2a83b5"}
|
||||
{"sample_id": "-s9qJ7ATP7w/1", "video_id": "-s9qJ7ATP7w", "clip_id": "1", "text": "But the hardest thing in life to learn, is to lose", "label": 0.6666666865348816, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/1.mp4", "duration_s": 4.791992, "ctc_inference_succeeded": true, "word_count": 11, "word_alignment_valid_count": 11, "audio_raw_length": 460, "audio_valid_length": 460, "audio_feature_dim": 25, "vision_raw_length": 24, "vision_valid_length": 24, "vision_feature_dim": 192, "face_blendshape_valid_length": 24, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 140, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.942, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__1.npz", "feature_file_bytes": 58350, "feature_file_sha256": "cc94c7c592ee6d42ad799825eedbcdfcc0341834c4d79ffb246dfbaafe9c87fd"}
|
||||
{"sample_id": "-s9qJ7ATP7w/0", "video_id": "-s9qJ7ATP7w", "clip_id": "0", "text": "they have doubt, they have fear, they lose in a Ferrari race, or they lose in a race, and then they just give up", "label": -0.3333333432674408, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/0.mp4", "duration_s": 6.8, "ctc_inference_succeeded": true, "word_count": 24, "word_alignment_valid_count": 24, "audio_raw_length": 667, "audio_valid_length": 667, "audio_feature_dim": 25, "vision_raw_length": 34, "vision_valid_length": 34, "vision_feature_dim": 192, "face_blendshape_valid_length": 31, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 204, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 2.142, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__0.npz", "feature_file_bytes": 96329, "feature_file_sha256": "b0fb54a85e566807cb47c6bdecfe451186e44c63710261c8bb04c9f01b7733d0"}
|
||||
{"sample_id": "-s9qJ7ATP7w/5", "video_id": "-s9qJ7ATP7w", "clip_id": "5", "text": "I have been beat up and put down and everything that can go wrong, has gone wrong for me", "label": -2.0, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/5.mp4", "duration_s": 8.561003, "ctc_inference_succeeded": true, "word_count": 19, "word_alignment_valid_count": 19, "audio_raw_length": 835, "audio_valid_length": 835, "audio_feature_dim": 25, "vision_raw_length": 43, "vision_valid_length": 43, "vision_feature_dim": 192, "face_blendshape_valid_length": 43, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 253, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.277, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__5.npz", "feature_file_bytes": 99292, "feature_file_sha256": "6ecf85da4fcacecc15338678cf8cc5c6a5f3af0128a88b8d9298286b0a4afb26"}
|
||||
{"sample_id": "-s9qJ7ATP7w/4", "video_id": "-s9qJ7ATP7w", "clip_id": "4", "text": "I have lost at everything you can imagine, seriously", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/4.mp4", "duration_s": 4.427018, "ctc_inference_succeeded": true, "word_count": 9, "word_alignment_valid_count": 9, "audio_raw_length": 420, "audio_valid_length": 420, "audio_feature_dim": 25, "vision_raw_length": 22, "vision_valid_length": 22, "vision_feature_dim": 192, "face_blendshape_valid_length": 15, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 129, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.911, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__4.npz", "feature_file_bytes": 51817, "feature_file_sha256": "002ce0a58ed37703e00cf3458ab59cc049db47bd7c979615cad3682cdbaf0838"}
|
||||
{"sample_id": "-s9qJ7ATP7w/7", "video_id": "-s9qJ7ATP7w", "clip_id": "7", "text": "I used to work for Warren Avis, the guy who started Avis Rent a Car, and he said to me one day, \"Robert, \"what's the purpose of business", "label": 1.0, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/7.mp4", "duration_s": 6.966016, "ctc_inference_succeeded": true, "word_count": 28, "word_alignment_valid_count": 28, "audio_raw_length": 679, "audio_valid_length": 679, "audio_feature_dim": 25, "vision_raw_length": 35, "vision_valid_length": 35, "vision_feature_dim": 192, "face_blendshape_valid_length": 20, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 207, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.075, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__7.npz", "feature_file_bytes": 101098, "feature_file_sha256": "85a1bcab56ec084155d7d8bc35f288bf9480ce26e75caaf14e35fc2f1e8b48ba"}
|
||||
{"sample_id": "-s9qJ7ATP7w/6", "video_id": "-s9qJ7ATP7w", "clip_id": "6", "text": "But I just kept going", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/6.mp4", "duration_s": 2.475, "ctc_inference_succeeded": true, "word_count": 5, "word_alignment_valid_count": 5, "audio_raw_length": 227, "audio_valid_length": 227, "audio_feature_dim": 25, "vision_raw_length": 12, "vision_valid_length": 12, "vision_feature_dim": 192, "face_blendshape_valid_length": 10, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 71, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 0.804, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__6.npz", "feature_file_bytes": 30573, "feature_file_sha256": "68001547dea974adef9554ce2a88d10e746552ec61a8f69c26250d18300fa1b6"}
|
||||
{"sample_id": "-s9qJ7ATP7w/8", "video_id": "-s9qJ7ATP7w", "clip_id": "8", "text": "\" And I said, \"Oh, make a profit, and all these other things", "label": 1.3333333730697632, "annotation": "Positive", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-s9qJ7ATP7w/8.mp4", "duration_s": 3.294987, "ctc_inference_succeeded": true, "word_count": 13, "word_alignment_valid_count": 12, "audio_raw_length": 314, "audio_valid_length": 314, "audio_feature_dim": 25, "vision_raw_length": 17, "vision_valid_length": 17, "vision_feature_dim": 192, "face_blendshape_valid_length": 15, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 97, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": ["ctc_words_fallback:1"], "processing_seconds": 0.863, "feature_file": "outputs/q1_features/features/-s9qJ7ATP7w__8.npz", "feature_file_bytes": 52875, "feature_file_sha256": "0e7a2e709dd34a73485db259ac88f7a8fef9cd065910530d361579766cc95b6f"}
|
||||
{"sample_id": "-yRb-Jum7EQ/1", "video_id": "-yRb-Jum7EQ", "clip_id": "1", "text": "it comes with the assistance and agitation of states and regimes, Yesterday Iran announced that it will finance the families of the terrorists and murderers this shows that Iran, even after the nuclear agreement, is continuing to aid terrorism, including Palestinian terrorism, Hezbollah terrorism and its assistance to Hamas.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-yRb-Jum7EQ/1.mp4", "duration_s": 29.288021, "ctc_inference_succeeded": true, "word_count": 49, "word_alignment_valid_count": 49, "audio_raw_length": 2906, "audio_valid_length": 2906, "audio_feature_dim": 25, "vision_raw_length": 146, "vision_valid_length": 146, "vision_feature_dim": 192, "face_blendshape_valid_length": 136, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 875, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 2.523, "feature_file": "outputs/q1_features/features/-yRb-Jum7EQ__1.npz", "feature_file_bytes": 263653, "feature_file_sha256": "a4ad7e2f132c3aa0b5e13048eab783e39398a20158fc1246f925bbb99acc0864"}
|
||||
{"sample_id": "-yRb-Jum7EQ/5", "video_id": "-yRb-Jum7EQ", "clip_id": "5", "text": "Yesterday Eliav Gelman lost his life in another terrorist attack, not by the students of terrorism, but by those who teach terrorism, a Palestinian teacher.", "label": -0.6666666865348816, "annotation": "Negative", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-yRb-Jum7EQ/5.mp4", "duration_s": 13.16901, "ctc_inference_succeeded": true, "word_count": 25, "word_alignment_valid_count": 25, "audio_raw_length": 1300, "audio_valid_length": 1300, "audio_feature_dim": 25, "vision_raw_length": 66, "vision_valid_length": 66, "vision_feature_dim": 192, "face_blendshape_valid_length": 66, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 394, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.409, "feature_file": "outputs/q1_features/features/-yRb-Jum7EQ__5.npz", "feature_file_bytes": 139890, "feature_file_sha256": "7f4a3740c7713dd89634f895dce748759b2d17fc1ea10387310234a966a92176"}
|
||||
{"sample_id": "-yRb-Jum7EQ/6", "video_id": "-yRb-Jum7EQ", "clip_id": "6", "text": "Therefore, the world needs to stand with Israel against this incitement, which is the number one cause of terrorism.", "label": 0.0, "annotation": "Neutral", "video_path": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/-yRb-Jum7EQ/6.mp4", "duration_s": 11.241995, "ctc_inference_succeeded": true, "word_count": 19, "word_alignment_valid_count": 19, "audio_raw_length": 1120, "audio_valid_length": 1120, "audio_feature_dim": 25, "vision_raw_length": 56, "vision_valid_length": 56, "vision_feature_dim": 192, "face_blendshape_valid_length": 56, "face_blendshape_feature_dim": 52, "vision_decoded_source_frames": 336, "text_feature_dim": 768, "alignment_granularity": "transcript word; Audio/Vision pooled over forced CTC word interval", "errors": {}, "warnings": [], "processing_seconds": 1.437, "feature_file": "outputs/q1_features/features/-yRb-Jum7EQ__6.npz", "feature_file_bytes": 112532, "feature_file_sha256": "5e45984ca8eb914de964d3febc9f4d2499600ba8679af2038fa92f3cf1df7a29"}
|
||||
@@ -0,0 +1,301 @@
|
||||
sample_id,video_id,clip_id,modality,effective_duration_s,feature_dimension,sequence_length,valid_length,padding_rule,alignment_granularity,source_time_mapping,feature_file,status,errors,warnings
|
||||
-3g5yACwYnA/13,-3g5yACwYnA,13,text,5.513997,768,15,15,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__13.npz,ok,{},[]
|
||||
-3g5yACwYnA/13,-3g5yACwYnA,13,audio,5.513997,25,535,535,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__13.npz,ok,{},[]
|
||||
-3g5yACwYnA/13,-3g5yACwYnA,13,vision,5.513997,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__13.npz,ok,{},[]
|
||||
-3g5yACwYnA/3,-3g5yACwYnA,3,text,14.388997,768,29,29,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__3.npz,ok,{},[]
|
||||
-3g5yACwYnA/3,-3g5yACwYnA,3,audio,14.388997,25,1428,1428,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__3.npz,ok,{},[]
|
||||
-3g5yACwYnA/3,-3g5yACwYnA,3,vision,14.388997,192,72,72,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__3.npz,ok,{},[]
|
||||
-3g5yACwYnA/2,-3g5yACwYnA,2,text,9.39401,768,14,14,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__2.npz,ok,{},[]
|
||||
-3g5yACwYnA/2,-3g5yACwYnA,2,audio,9.39401,25,919,919,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__2.npz,ok,{},[]
|
||||
-3g5yACwYnA/2,-3g5yACwYnA,2,vision,9.39401,192,47,47,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__2.npz,ok,{},[]
|
||||
-3g5yACwYnA/9,-3g5yACwYnA,9,text,8.816992,768,21,21,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__9.npz,ok,{},[]
|
||||
-3g5yACwYnA/9,-3g5yACwYnA,9,audio,8.816992,25,865,865,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__9.npz,ok,{},[]
|
||||
-3g5yACwYnA/9,-3g5yACwYnA,9,vision,8.816992,192,44,44,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3g5yACwYnA__9.npz,ok,{},[]
|
||||
-3nNcZdcdvU/5,-3nNcZdcdvU,5,text,7.867969,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3nNcZdcdvU__5.npz,ok,{},[]
|
||||
-3nNcZdcdvU/5,-3nNcZdcdvU,5,audio,7.867969,25,774,774,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3nNcZdcdvU__5.npz,ok,{},[]
|
||||
-3nNcZdcdvU/5,-3nNcZdcdvU,5,vision,7.867969,192,40,40,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-3nNcZdcdvU__5.npz,ok,{},[]
|
||||
-HwX2H8Z4hY/2,-HwX2H8Z4hY,2,text,3.982031,768,8,7,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__2.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/2,-HwX2H8Z4hY,2,audio,3.982031,25,387,387,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__2.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/2,-HwX2H8Z4hY,2,vision,3.982031,192,20,20,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__2.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/5,-HwX2H8Z4hY,5,text,5.652995,768,10,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/5,-HwX2H8Z4hY,5,audio,5.652995,25,550,550,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/5,-HwX2H8Z4hY,5,vision,5.652995,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-HwX2H8Z4hY/6,-HwX2H8Z4hY,6,text,3.358008,768,7,7,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__6.npz,ok,{},[]
|
||||
-HwX2H8Z4hY/6,-HwX2H8Z4hY,6,audio,3.358008,25,321,321,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__6.npz,ok,{},[]
|
||||
-HwX2H8Z4hY/6,-HwX2H8Z4hY,6,vision,3.358008,192,17,17,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__6.npz,ok,{},[]
|
||||
-HwX2H8Z4hY/9,-HwX2H8Z4hY,9,text,7.733984,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-HwX2H8Z4hY/9,-HwX2H8Z4hY,9,audio,7.733984,25,759,759,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-HwX2H8Z4hY/9,-HwX2H8Z4hY,9,vision,7.733984,192,39,39,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HwX2H8Z4hY__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/1,-NFrJFQijFE,1,text,5.746,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/1,-NFrJFQijFE,1,audio,5.746,25,561,561,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/1,-NFrJFQijFE,1,vision,5.746,192,29,29,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/2,-NFrJFQijFE,2,text,6.856,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/2,-NFrJFQijFE,2,audio,6.856,25,665,665,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-NFrJFQijFE/2,-NFrJFQijFE,2,vision,6.856,192,34,34,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-NFrJFQijFE__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-THoVjtIkeU/12,-THoVjtIkeU,12,text,14.896029,768,39,39,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__12.npz,ok,{},[]
|
||||
-THoVjtIkeU/12,-THoVjtIkeU,12,audio,14.896029,25,1476,1476,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__12.npz,ok,{},[]
|
||||
-THoVjtIkeU/12,-THoVjtIkeU,12,vision,14.896029,192,75,75,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__12.npz,ok,{},[]
|
||||
-THoVjtIkeU/2,-THoVjtIkeU,2,text,4.291992,768,10,10,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__2.npz,ok,{},[]
|
||||
-THoVjtIkeU/2,-THoVjtIkeU,2,audio,4.291992,25,419,419,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__2.npz,ok,{},[]
|
||||
-THoVjtIkeU/2,-THoVjtIkeU,2,vision,4.291992,192,22,22,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__2.npz,ok,{},[]
|
||||
-THoVjtIkeU/6,-THoVjtIkeU,6,text,8.097005,768,30,30,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__6.npz,ok,{},[]
|
||||
-THoVjtIkeU/6,-THoVjtIkeU,6,audio,8.097005,25,794,794,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__6.npz,ok,{},[]
|
||||
-THoVjtIkeU/6,-THoVjtIkeU,6,vision,8.097005,192,41,41,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-THoVjtIkeU__6.npz,ok,{},[]
|
||||
-UuX1xuaiiE/1,-UuX1xuaiiE,1,text,10.35,768,27,27,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__1.npz,ok,{},[]
|
||||
-UuX1xuaiiE/1,-UuX1xuaiiE,1,audio,10.35,25,1022,1022,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__1.npz,ok,{},[]
|
||||
-UuX1xuaiiE/1,-UuX1xuaiiE,1,vision,10.35,192,52,52,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__1.npz,ok,{},[]
|
||||
-UuX1xuaiiE/0,-UuX1xuaiiE,0,text,3.633333,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__0.npz,ok,{},[]
|
||||
-UuX1xuaiiE/0,-UuX1xuaiiE,0,audio,3.633333,25,353,353,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__0.npz,ok,{},[]
|
||||
-UuX1xuaiiE/0,-UuX1xuaiiE,0,vision,3.633333,192,19,19,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__0.npz,ok,{},[]
|
||||
-UuX1xuaiiE/3,-UuX1xuaiiE,3,text,4.130013,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__3.npz,ok,{},[]
|
||||
-UuX1xuaiiE/3,-UuX1xuaiiE,3,audio,4.130013,25,399,399,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__3.npz,ok,{},[]
|
||||
-UuX1xuaiiE/3,-UuX1xuaiiE,3,vision,4.130013,192,21,21,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__3.npz,ok,{},[]
|
||||
-UuX1xuaiiE/6,-UuX1xuaiiE,6,text,8.113997,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__6.npz,ok,{},[]
|
||||
-UuX1xuaiiE/6,-UuX1xuaiiE,6,audio,8.113997,25,790,790,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__6.npz,ok,{},[]
|
||||
-UuX1xuaiiE/6,-UuX1xuaiiE,6,vision,8.113997,192,40,40,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UuX1xuaiiE__6.npz,ok,{},[]
|
||||
-a55Q6RWvTA/3,-a55Q6RWvTA,3,text,22.153971,768,65,65,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-a55Q6RWvTA__3.npz,ok,{},[]
|
||||
-a55Q6RWvTA/3,-a55Q6RWvTA,3,audio,22.153971,25,2204,2204,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-a55Q6RWvTA__3.npz,ok,{},[]
|
||||
-a55Q6RWvTA/3,-a55Q6RWvTA,3,vision,22.153971,192,111,111,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-a55Q6RWvTA__3.npz,ok,{},[]
|
||||
-aNfi7CP8vM/7,-aNfi7CP8vM,7,text,8.694987,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aNfi7CP8vM__7.npz,ok,{},[]
|
||||
-aNfi7CP8vM/7,-aNfi7CP8vM,7,audio,8.694987,25,849,849,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aNfi7CP8vM__7.npz,ok,{},[]
|
||||
-aNfi7CP8vM/7,-aNfi7CP8vM,7,vision,8.694987,192,43,43,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aNfi7CP8vM__7.npz,ok,{},[]
|
||||
-aqamKhZ1Ec/0,-aqamKhZ1Ec,0,text,10.966667,768,14,13,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aqamKhZ1Ec__0.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-aqamKhZ1Ec/0,-aqamKhZ1Ec,0,audio,10.966667,25,1085,1085,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aqamKhZ1Ec__0.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-aqamKhZ1Ec/0,-aqamKhZ1Ec,0,vision,10.966667,192,55,55,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-aqamKhZ1Ec__0.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-dxfTGcXJoc/1,-dxfTGcXJoc,1,text,16.161003,768,36,36,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__1.npz,ok,{},[]
|
||||
-dxfTGcXJoc/1,-dxfTGcXJoc,1,audio,16.161003,25,1597,1597,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__1.npz,ok,{},[]
|
||||
-dxfTGcXJoc/1,-dxfTGcXJoc,1,vision,16.161003,192,81,81,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__1.npz,ok,{},[]
|
||||
-dxfTGcXJoc/0,-dxfTGcXJoc,0,text,20.5,768,41,38,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__0.npz,ok_with_warning,{},"[""ctc_words_fallback:3""]"
|
||||
-dxfTGcXJoc/0,-dxfTGcXJoc,0,audio,20.5,25,2037,2037,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__0.npz,ok_with_warning,{},"[""ctc_words_fallback:3""]"
|
||||
-dxfTGcXJoc/0,-dxfTGcXJoc,0,vision,20.5,192,103,103,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__0.npz,ok_with_warning,{},"[""ctc_words_fallback:3""]"
|
||||
-dxfTGcXJoc/2,-dxfTGcXJoc,2,text,16.697982,768,34,32,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__2.npz,ok_with_warning,{},"[""ctc_words_fallback:2""]"
|
||||
-dxfTGcXJoc/2,-dxfTGcXJoc,2,audio,16.697982,25,1659,1659,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__2.npz,ok_with_warning,{},"[""ctc_words_fallback:2""]"
|
||||
-dxfTGcXJoc/2,-dxfTGcXJoc,2,vision,16.697982,192,84,84,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__2.npz,ok_with_warning,{},"[""ctc_words_fallback:2""]"
|
||||
-dxfTGcXJoc/6,-dxfTGcXJoc,6,text,12.735026,768,27,27,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__6.npz,ok,{},[]
|
||||
-dxfTGcXJoc/6,-dxfTGcXJoc,6,audio,12.735026,25,1258,1258,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__6.npz,ok,{},[]
|
||||
-dxfTGcXJoc/6,-dxfTGcXJoc,6,vision,12.735026,192,64,64,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-dxfTGcXJoc__6.npz,ok,{},[]
|
||||
-egA8-b7-3M/26,-egA8-b7-3M,26,text,6.03099,768,15,15,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__26.npz,ok,{},[]
|
||||
-egA8-b7-3M/26,-egA8-b7-3M,26,audio,6.03099,25,588,588,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__26.npz,ok,{},[]
|
||||
-egA8-b7-3M/26,-egA8-b7-3M,26,vision,6.03099,192,30,30,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__26.npz,ok,{},[]
|
||||
-egA8-b7-3M/17,-egA8-b7-3M,17,text,7.271029,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__17.npz,ok,{},[]
|
||||
-egA8-b7-3M/17,-egA8-b7-3M,17,audio,7.271029,25,705,705,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__17.npz,ok,{},[]
|
||||
-egA8-b7-3M/17,-egA8-b7-3M,17,vision,7.271029,192,36,36,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__17.npz,ok,{},[]
|
||||
-egA8-b7-3M/18,-egA8-b7-3M,18,text,8.386003,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__18.npz,ok,{},[]
|
||||
-egA8-b7-3M/18,-egA8-b7-3M,18,audio,8.386003,25,822,822,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__18.npz,ok,{},[]
|
||||
-egA8-b7-3M/18,-egA8-b7-3M,18,vision,8.386003,192,42,42,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__18.npz,ok,{},[]
|
||||
-egA8-b7-3M/16,-egA8-b7-3M,16,text,5.538021,768,11,11,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__16.npz,ok,{},[]
|
||||
-egA8-b7-3M/16,-egA8-b7-3M,16,audio,5.538021,25,544,544,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__16.npz,ok,{},[]
|
||||
-egA8-b7-3M/16,-egA8-b7-3M,16,vision,5.538021,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__16.npz,ok,{},[]
|
||||
-egA8-b7-3M/13,-egA8-b7-3M,13,text,4.183984,768,11,11,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__13.npz,ok,{},[]
|
||||
-egA8-b7-3M/13,-egA8-b7-3M,13,audio,4.183984,25,398,398,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__13.npz,ok,{},[]
|
||||
-egA8-b7-3M/13,-egA8-b7-3M,13,vision,4.183984,192,21,21,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__13.npz,ok,{},[]
|
||||
-egA8-b7-3M/1,-egA8-b7-3M,1,text,10.266016,768,20,19,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-egA8-b7-3M/1,-egA8-b7-3M,1,audio,10.266016,25,1011,1011,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-egA8-b7-3M/1,-egA8-b7-3M,1,vision,10.266016,192,51,51,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-egA8-b7-3M/6,-egA8-b7-3M,6,text,6.264974,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__6.npz,ok,{},[]
|
||||
-egA8-b7-3M/6,-egA8-b7-3M,6,audio,6.264974,25,614,614,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__6.npz,ok,{},[]
|
||||
-egA8-b7-3M/6,-egA8-b7-3M,6,vision,6.264974,192,32,32,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__6.npz,ok,{},[]
|
||||
-egA8-b7-3M/9,-egA8-b7-3M,9,text,5.089974,768,10,10,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__9.npz,ok,{},[]
|
||||
-egA8-b7-3M/9,-egA8-b7-3M,9,audio,5.089974,25,489,489,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__9.npz,ok,{},[]
|
||||
-egA8-b7-3M/9,-egA8-b7-3M,9,vision,5.089974,192,25,25,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__9.npz,ok,{},[]
|
||||
-egA8-b7-3M/20,-egA8-b7-3M,20,text,6.644987,768,20,20,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__20.npz,ok,{},[]
|
||||
-egA8-b7-3M/20,-egA8-b7-3M,20,audio,6.644987,25,643,643,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__20.npz,ok,{},[]
|
||||
-egA8-b7-3M/20,-egA8-b7-3M,20,vision,6.644987,192,33,33,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-egA8-b7-3M__20.npz,ok,{},[]
|
||||
-iRBcNs9oI8/3,-iRBcNs9oI8,3,text,5.621,768,8,8,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__3.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/3,-iRBcNs9oI8,3,audio,5.621,25,549,549,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__3.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/3,-iRBcNs9oI8,3,vision,5.621,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__3.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/7,-iRBcNs9oI8,7,text,4.104,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/7,-iRBcNs9oI8,7,audio,4.104,25,396,396,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/7,-iRBcNs9oI8,7,vision,4.104,192,20,20,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/6,-iRBcNs9oI8,6,text,2.903,768,5,5,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/6,-iRBcNs9oI8,6,audio,2.903,25,278,278,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/6,-iRBcNs9oI8,6,vision,2.903,192,15,15,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/9,-iRBcNs9oI8,9,text,3.416,768,5,5,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/9,-iRBcNs9oI8,9,audio,3.416,25,333,333,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/9,-iRBcNs9oI8,9,vision,3.416,192,17,17,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__9.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/8,-iRBcNs9oI8,8,text,8.093,768,21,21,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__8.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/8,-iRBcNs9oI8,8,audio,8.093,25,798,798,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__8.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-iRBcNs9oI8/8,-iRBcNs9oI8,8,vision,8.093,192,41,41,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-iRBcNs9oI8__8.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-lzEya4AM_4/5,-lzEya4AM_4,5,text,7.675,768,19,19,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__5.npz,ok,{},[]
|
||||
-lzEya4AM_4/5,-lzEya4AM_4,5,audio,7.675,25,752,752,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__5.npz,ok,{},[]
|
||||
-lzEya4AM_4/5,-lzEya4AM_4,5,vision,7.675,192,39,39,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__5.npz,ok,{},[]
|
||||
-lzEya4AM_4/6,-lzEya4AM_4,6,text,14.791992,768,43,43,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__6.npz,ok,{},[]
|
||||
-lzEya4AM_4/6,-lzEya4AM_4,6,audio,14.791992,25,1470,1470,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__6.npz,ok,{},[]
|
||||
-lzEya4AM_4/6,-lzEya4AM_4,6,vision,14.791992,192,74,74,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-lzEya4AM_4__6.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/1,-mJ2ud6oKI8,1,text,6.103,768,13,13,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/1,-mJ2ud6oKI8,1,audio,6.103,25,601,601,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/1,-mJ2ud6oKI8,1,vision,6.103,192,31,31,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__1.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/2,-mJ2ud6oKI8,2,text,5.731,768,11,11,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/2,-mJ2ud6oKI8,2,audio,5.731,25,566,566,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/2,-mJ2ud6oKI8,2,vision,5.731,192,29,29,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__2.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-mJ2ud6oKI8/6,-mJ2ud6oKI8,6,text,2.257,768,5,5,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__6.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/6,-mJ2ud6oKI8,6,audio,2.257,25,218,218,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__6.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/6,-mJ2ud6oKI8,6,vision,2.257,192,12,12,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__6.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/9,-mJ2ud6oKI8,9,text,7.033,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__9.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/9,-mJ2ud6oKI8,9,audio,7.033,25,686,686,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__9.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/9,-mJ2ud6oKI8,9,vision,7.033,192,35,35,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__9.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/8,-mJ2ud6oKI8,8,text,4.192,768,11,11,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__8.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/8,-mJ2ud6oKI8,8,audio,4.192,25,413,413,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__8.npz,ok,{},[]
|
||||
-mJ2ud6oKI8/8,-mJ2ud6oKI8,8,vision,4.192,192,21,21,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mJ2ud6oKI8__8.npz,ok,{},[]
|
||||
-mqbVkbCndg/0,-mqbVkbCndg,0,text,6.466667,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mqbVkbCndg__0.npz,ok,{},[]
|
||||
-mqbVkbCndg/0,-mqbVkbCndg,0,audio,6.466667,25,634,634,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mqbVkbCndg__0.npz,ok,{},[]
|
||||
-mqbVkbCndg/0,-mqbVkbCndg,0,vision,6.466667,192,33,33,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-mqbVkbCndg__0.npz,ok,{},[]
|
||||
-t217m2on-s/2,-t217m2on-s,2,text,5.686003,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__2.npz,ok,{},[]
|
||||
-t217m2on-s/2,-t217m2on-s,2,audio,5.686003,25,559,559,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__2.npz,ok,{},[]
|
||||
-t217m2on-s/2,-t217m2on-s,2,vision,5.686003,192,29,29,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__2.npz,ok,{},[]
|
||||
-t217m2on-s/7,-t217m2on-s,7,text,17.183008,768,45,45,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__7.npz,ok,{},[]
|
||||
-t217m2on-s/7,-t217m2on-s,7,audio,17.183008,25,1698,1698,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__7.npz,ok,{},[]
|
||||
-t217m2on-s/7,-t217m2on-s,7,vision,17.183008,192,86,86,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-t217m2on-s__7.npz,ok,{},[]
|
||||
-tANM6ETl_M/3,-tANM6ETl_M,3,text,6.758008,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tANM6ETl_M__3.npz,ok,{},[]
|
||||
-tANM6ETl_M/3,-tANM6ETl_M,3,audio,6.758008,25,656,656,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tANM6ETl_M__3.npz,ok,{},[]
|
||||
-tANM6ETl_M/3,-tANM6ETl_M,3,vision,6.758008,192,34,34,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tANM6ETl_M__3.npz,ok,{},[]
|
||||
-tPCytz4rww/11,-tPCytz4rww,11,text,5.466992,768,17,17,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__11.npz,ok,{},[]
|
||||
-tPCytz4rww/11,-tPCytz4rww,11,audio,5.466992,25,533,533,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__11.npz,ok,{},[]
|
||||
-tPCytz4rww/11,-tPCytz4rww,11,vision,5.466992,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__11.npz,ok,{},[]
|
||||
-tPCytz4rww/10,-tPCytz4rww,10,text,4.788997,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__10.npz,ok,{},[]
|
||||
-tPCytz4rww/10,-tPCytz4rww,10,audio,4.788997,25,463,463,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__10.npz,ok,{},[]
|
||||
-tPCytz4rww/10,-tPCytz4rww,10,vision,4.788997,192,24,24,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__10.npz,ok,{},[]
|
||||
-tPCytz4rww/12,-tPCytz4rww,12,text,11.863997,768,26,26,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__12.npz,ok,{},[]
|
||||
-tPCytz4rww/12,-tPCytz4rww,12,audio,11.863997,25,1169,1169,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__12.npz,ok,{},[]
|
||||
-tPCytz4rww/12,-tPCytz4rww,12,vision,11.863997,192,59,59,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__12.npz,ok,{},[]
|
||||
-tPCytz4rww/16,-tPCytz4rww,16,text,7.20599,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__16.npz,ok,{},[]
|
||||
-tPCytz4rww/16,-tPCytz4rww,16,audio,7.20599,25,709,709,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__16.npz,ok,{},[]
|
||||
-tPCytz4rww/16,-tPCytz4rww,16,vision,7.20599,192,36,36,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__16.npz,ok,{},[]
|
||||
-tPCytz4rww/18,-tPCytz4rww,18,text,6.644987,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__18.npz,ok,{},[]
|
||||
-tPCytz4rww/18,-tPCytz4rww,18,audio,6.644987,25,652,652,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__18.npz,ok,{},[]
|
||||
-tPCytz4rww/18,-tPCytz4rww,18,vision,6.644987,192,34,34,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-tPCytz4rww__18.npz,ok,{},[]
|
||||
-vxjVxOeScU/4,-vxjVxOeScU,4,text,9.127018,768,21,21,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-vxjVxOeScU__4.npz,ok,{},[]
|
||||
-vxjVxOeScU/4,-vxjVxOeScU,4,audio,9.127018,25,899,899,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-vxjVxOeScU__4.npz,ok,{},[]
|
||||
-vxjVxOeScU/4,-vxjVxOeScU,4,vision,9.127018,192,46,46,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-vxjVxOeScU__4.npz,ok,{},[]
|
||||
-wMB_hJL-3o/7,-wMB_hJL-3o,7,text,6.04401,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wMB_hJL-3o__7.npz,ok,{},[]
|
||||
-wMB_hJL-3o/7,-wMB_hJL-3o,7,audio,6.04401,25,593,593,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wMB_hJL-3o__7.npz,ok,{},[]
|
||||
-wMB_hJL-3o/7,-wMB_hJL-3o,7,vision,6.04401,192,31,31,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wMB_hJL-3o__7.npz,ok,{},[]
|
||||
-wny0OAz3g8/1,-wny0OAz3g8,1,text,6.84401,768,23,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-wny0OAz3g8/1,-wny0OAz3g8,1,audio,6.84401,25,673,673,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-wny0OAz3g8/1,-wny0OAz3g8,1,vision,6.84401,192,35,35,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__1.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-wny0OAz3g8/0,-wny0OAz3g8,0,text,3.333333,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__0.npz,ok,{},[]
|
||||
-wny0OAz3g8/0,-wny0OAz3g8,0,audio,3.333333,25,323,323,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__0.npz,ok,{},[]
|
||||
-wny0OAz3g8/0,-wny0OAz3g8,0,vision,3.333333,192,17,17,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__0.npz,ok,{},[]
|
||||
-wny0OAz3g8/3,-wny0OAz3g8,3,text,6.146029,768,20,20,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__3.npz,ok,{},[]
|
||||
-wny0OAz3g8/3,-wny0OAz3g8,3,audio,6.146029,25,605,605,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__3.npz,ok,{},[]
|
||||
-wny0OAz3g8/3,-wny0OAz3g8,3,vision,6.146029,192,31,31,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__3.npz,ok,{},[]
|
||||
-wny0OAz3g8/2,-wny0OAz3g8,2,text,6.686979,768,23,23,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__2.npz,ok,{},[]
|
||||
-wny0OAz3g8/2,-wny0OAz3g8,2,audio,6.686979,25,648,648,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__2.npz,ok,{},[]
|
||||
-wny0OAz3g8/2,-wny0OAz3g8,2,vision,6.686979,192,33,33,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__2.npz,ok,{},[]
|
||||
-wny0OAz3g8/5,-wny0OAz3g8,5,text,6.911979,768,20,20,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__5.npz,ok,{},[]
|
||||
-wny0OAz3g8/5,-wny0OAz3g8,5,audio,6.911979,25,670,670,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__5.npz,ok,{},[]
|
||||
-wny0OAz3g8/5,-wny0OAz3g8,5,vision,6.911979,192,34,34,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__5.npz,ok,{},[]
|
||||
-wny0OAz3g8/7,-wny0OAz3g8,7,text,8.067969,768,29,29,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__7.npz,ok,{},[]
|
||||
-wny0OAz3g8/7,-wny0OAz3g8,7,audio,8.067969,25,787,787,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__7.npz,ok,{},[]
|
||||
-wny0OAz3g8/7,-wny0OAz3g8,7,vision,8.067969,192,40,40,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__7.npz,ok,{},[]
|
||||
-wny0OAz3g8/9,-wny0OAz3g8,9,text,6.213021,768,20,20,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__9.npz,ok,{},[]
|
||||
-wny0OAz3g8/9,-wny0OAz3g8,9,audio,6.213021,25,600,600,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__9.npz,ok,{},[]
|
||||
-wny0OAz3g8/9,-wny0OAz3g8,9,vision,6.213021,192,31,31,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-wny0OAz3g8__9.npz,ok,{},[]
|
||||
-571d8cVauQ/0,-571d8cVauQ,0,text,5.066667,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__0.npz,ok,{},[]
|
||||
-571d8cVauQ/0,-571d8cVauQ,0,audio,5.066667,25,495,495,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__0.npz,ok,{},[]
|
||||
-571d8cVauQ/0,-571d8cVauQ,0,vision,5.066667,192,26,26,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__0.npz,ok,{},[]
|
||||
-571d8cVauQ/5,-571d8cVauQ,5,text,15.272982,768,43,43,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__5.npz,ok,{},[]
|
||||
-571d8cVauQ/5,-571d8cVauQ,5,audio,15.272982,25,1507,1507,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__5.npz,ok,{},[]
|
||||
-571d8cVauQ/5,-571d8cVauQ,5,vision,15.272982,192,76,76,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-571d8cVauQ__5.npz,ok,{},[]
|
||||
-I_e4mIh0yE/1,-I_e4mIh0yE,1,text,7.622005,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__1.npz,ok,{},[]
|
||||
-I_e4mIh0yE/1,-I_e4mIh0yE,1,audio,7.622005,25,740,740,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__1.npz,ok,{},[]
|
||||
-I_e4mIh0yE/1,-I_e4mIh0yE,1,vision,7.622005,192,38,38,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__1.npz,ok,{},[]
|
||||
-I_e4mIh0yE/3,-I_e4mIh0yE,3,text,9.163021,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__3.npz,ok,{},[]
|
||||
-I_e4mIh0yE/3,-I_e4mIh0yE,3,audio,9.163021,25,895,895,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__3.npz,ok,{},[]
|
||||
-I_e4mIh0yE/3,-I_e4mIh0yE,3,vision,9.163021,192,46,46,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-I_e4mIh0yE__3.npz,ok,{},[]
|
||||
-UacrmKiTn4/10,-UacrmKiTn4,10,text,7.361979,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__10.npz,ok,{},[]
|
||||
-UacrmKiTn4/10,-UacrmKiTn4,10,audio,7.361979,25,720,720,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__10.npz,ok,{},[]
|
||||
-UacrmKiTn4/10,-UacrmKiTn4,10,vision,7.361979,192,37,37,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__10.npz,ok,{},[]
|
||||
-UacrmKiTn4/4,-UacrmKiTn4,4,text,4.741016,768,14,14,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__4.npz,ok,{},[]
|
||||
-UacrmKiTn4/4,-UacrmKiTn4,4,audio,4.741016,25,464,464,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__4.npz,ok,{},[]
|
||||
-UacrmKiTn4/4,-UacrmKiTn4,4,vision,4.741016,192,24,24,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UacrmKiTn4__4.npz,ok,{},[]
|
||||
-hnBHBN8p5A/7,-hnBHBN8p5A,7,text,7.372,768,13,13,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-hnBHBN8p5A/7,-hnBHBN8p5A,7,audio,7.372,25,726,726,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-hnBHBN8p5A/7,-hnBHBN8p5A,7,vision,7.372,192,36,36,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__7.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-hnBHBN8p5A/6,-hnBHBN8p5A,6,text,6.401,768,13,13,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-hnBHBN8p5A/6,-hnBHBN8p5A,6,audio,6.401,25,629,629,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-hnBHBN8p5A/6,-hnBHBN8p5A,6,vision,6.401,192,31,31,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-hnBHBN8p5A__6.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-qDkUB0GgYY/6,-qDkUB0GgYY,6,text,4.677995,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-qDkUB0GgYY__6.npz,ok,{},[]
|
||||
-qDkUB0GgYY/6,-qDkUB0GgYY,6,audio,4.677995,25,457,457,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-qDkUB0GgYY__6.npz,ok,{},[]
|
||||
-qDkUB0GgYY/6,-qDkUB0GgYY,6,vision,4.677995,192,24,24,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-qDkUB0GgYY__6.npz,ok,{},[]
|
||||
-uywlfIYOS8/4,-uywlfIYOS8,4,text,6.044987,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-uywlfIYOS8__4.npz,ok,{},[]
|
||||
-uywlfIYOS8/4,-uywlfIYOS8,4,audio,6.044987,25,584,584,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-uywlfIYOS8__4.npz,ok,{},[]
|
||||
-uywlfIYOS8/4,-uywlfIYOS8,4,vision,6.044987,192,30,30,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-uywlfIYOS8__4.npz,ok,{},[]
|
||||
-6rXp3zJ3kc/8,-6rXp3zJ3kc,8,text,12.805013,768,34,34,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-6rXp3zJ3kc__8.npz,ok,{},[]
|
||||
-6rXp3zJ3kc/8,-6rXp3zJ3kc,8,audio,12.805013,25,1269,1269,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-6rXp3zJ3kc__8.npz,ok,{},[]
|
||||
-6rXp3zJ3kc/8,-6rXp3zJ3kc,8,vision,12.805013,192,64,64,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-6rXp3zJ3kc__8.npz,ok,{},[]
|
||||
-9y-fZ3swSY/0,-9y-fZ3swSY,0,text,6.833333,768,22,22,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__0.npz,ok,{},[]
|
||||
-9y-fZ3swSY/0,-9y-fZ3swSY,0,audio,6.833333,25,671,671,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__0.npz,ok,{},[]
|
||||
-9y-fZ3swSY/0,-9y-fZ3swSY,0,vision,6.833333,192,35,35,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__0.npz,ok,{},[]
|
||||
-9y-fZ3swSY/4,-9y-fZ3swSY,4,text,2.821029,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__4.npz,ok,{},[]
|
||||
-9y-fZ3swSY/4,-9y-fZ3swSY,4,audio,2.821029,25,262,262,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__4.npz,ok,{},[]
|
||||
-9y-fZ3swSY/4,-9y-fZ3swSY,4,vision,2.821029,192,14,14,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__4.npz,ok,{},[]
|
||||
-9y-fZ3swSY/8,-9y-fZ3swSY,8,text,4.988997,768,12,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__8.npz,ok,{},[]
|
||||
-9y-fZ3swSY/8,-9y-fZ3swSY,8,audio,4.988997,25,487,487,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__8.npz,ok,{},[]
|
||||
-9y-fZ3swSY/8,-9y-fZ3swSY,8,vision,4.988997,192,25,25,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-9y-fZ3swSY__8.npz,ok,{},[]
|
||||
-AUZQgSxyPQ/2,-AUZQgSxyPQ,2,text,22.511003,768,41,41,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-AUZQgSxyPQ__2.npz,ok,{},[]
|
||||
-AUZQgSxyPQ/2,-AUZQgSxyPQ,2,audio,22.511003,25,2236,2236,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-AUZQgSxyPQ__2.npz,ok,{},[]
|
||||
-AUZQgSxyPQ/2,-AUZQgSxyPQ,2,vision,22.511003,192,113,113,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-AUZQgSxyPQ__2.npz,ok,{},[]
|
||||
-HeZS2-Prhc/2,-HeZS2-Prhc,2,text,8.261979,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HeZS2-Prhc__2.npz,ok,{},[]
|
||||
-HeZS2-Prhc/2,-HeZS2-Prhc,2,audio,8.261979,25,811,811,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HeZS2-Prhc__2.npz,ok,{},[]
|
||||
-HeZS2-Prhc/2,-HeZS2-Prhc,2,vision,8.261979,192,41,41,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-HeZS2-Prhc__2.npz,ok,{},[]
|
||||
-MeTTeMJBNc/0,-MeTTeMJBNc,0,text,9.3,768,21,21,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__0.npz,ok,{},[]
|
||||
-MeTTeMJBNc/0,-MeTTeMJBNc,0,audio,9.3,25,917,917,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__0.npz,ok,{},[]
|
||||
-MeTTeMJBNc/0,-MeTTeMJBNc,0,vision,9.3,192,47,47,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__0.npz,ok,{},[]
|
||||
-MeTTeMJBNc/13,-MeTTeMJBNc,13,text,5.430013,768,14,14,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__13.npz,ok,{},[]
|
||||
-MeTTeMJBNc/13,-MeTTeMJBNc,13,audio,5.430013,25,521,521,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__13.npz,ok,{},[]
|
||||
-MeTTeMJBNc/13,-MeTTeMJBNc,13,vision,5.430013,192,27,27,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__13.npz,ok,{},[]
|
||||
-MeTTeMJBNc/7,-MeTTeMJBNc,7,text,10.516992,768,31,31,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__7.npz,ok,{},[]
|
||||
-MeTTeMJBNc/7,-MeTTeMJBNc,7,audio,10.516992,25,1037,1037,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__7.npz,ok,{},[]
|
||||
-MeTTeMJBNc/7,-MeTTeMJBNc,7,vision,10.516992,192,53,53,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-MeTTeMJBNc__7.npz,ok,{},[]
|
||||
-RfYyzHpjk4/11,-RfYyzHpjk4,11,text,5.238997,768,17,17,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__11.npz,ok,{},[]
|
||||
-RfYyzHpjk4/11,-RfYyzHpjk4,11,audio,5.238997,25,503,503,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__11.npz,ok,{},[]
|
||||
-RfYyzHpjk4/11,-RfYyzHpjk4,11,vision,5.238997,192,26,26,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__11.npz,ok,{},[]
|
||||
-RfYyzHpjk4/8,-RfYyzHpjk4,8,text,4.588997,768,17,17,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__8.npz,ok,{},[]
|
||||
-RfYyzHpjk4/8,-RfYyzHpjk4,8,audio,4.588997,25,449,449,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__8.npz,ok,{},[]
|
||||
-RfYyzHpjk4/8,-RfYyzHpjk4,8,vision,4.588997,192,23,23,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__8.npz,ok,{},[]
|
||||
-RfYyzHpjk4/2,-RfYyzHpjk4,2,text,5.516016,768,25,25,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__2.npz,ok,{},[]
|
||||
-RfYyzHpjk4/2,-RfYyzHpjk4,2,audio,5.516016,25,535,535,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__2.npz,ok,{},[]
|
||||
-RfYyzHpjk4/2,-RfYyzHpjk4,2,vision,5.516016,192,28,28,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-RfYyzHpjk4__2.npz,ok,{},[]
|
||||
-UUCSKoHeMA/0,-UUCSKoHeMA,0,text,7.8,768,18,18,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UUCSKoHeMA__0.npz,ok,{},[]
|
||||
-UUCSKoHeMA/0,-UUCSKoHeMA,0,audio,7.8,25,769,769,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UUCSKoHeMA__0.npz,ok,{},[]
|
||||
-UUCSKoHeMA/0,-UUCSKoHeMA,0,vision,7.8,192,39,39,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-UUCSKoHeMA__0.npz,ok,{},[]
|
||||
-ri04Z7vwnc/0,-ri04Z7vwnc,0,text,2.807,768,8,8,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__0.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-ri04Z7vwnc/0,-ri04Z7vwnc,0,audio,2.807,25,272,272,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__0.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-ri04Z7vwnc/0,-ri04Z7vwnc,0,vision,2.807,192,14,14,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__0.npz,ok_with_warning,{},"[""no_face_blendshapes_detected""]"
|
||||
-ri04Z7vwnc/2,-ri04Z7vwnc,2,text,6.027,768,16,16,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__2.npz,ok,{},[]
|
||||
-ri04Z7vwnc/2,-ri04Z7vwnc,2,audio,6.027,25,587,587,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__2.npz,ok,{},[]
|
||||
-ri04Z7vwnc/2,-ri04Z7vwnc,2,vision,6.027,192,29,29,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__2.npz,ok,{},[]
|
||||
-ri04Z7vwnc/5,-ri04Z7vwnc,5,text,3.545,768,9,8,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-ri04Z7vwnc/5,-ri04Z7vwnc,5,audio,3.545,25,339,339,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-ri04Z7vwnc/5,-ri04Z7vwnc,5,vision,3.545,192,17,17,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-ri04Z7vwnc__5.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-s9qJ7ATP7w/1,-s9qJ7ATP7w,1,text,4.791992,768,11,11,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__1.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/1,-s9qJ7ATP7w,1,audio,4.791992,25,460,460,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__1.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/1,-s9qJ7ATP7w,1,vision,4.791992,192,24,24,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__1.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/0,-s9qJ7ATP7w,0,text,6.8,768,24,24,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__0.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/0,-s9qJ7ATP7w,0,audio,6.8,25,667,667,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__0.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/0,-s9qJ7ATP7w,0,vision,6.8,192,34,34,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__0.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/5,-s9qJ7ATP7w,5,text,8.561003,768,19,19,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__5.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/5,-s9qJ7ATP7w,5,audio,8.561003,25,835,835,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__5.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/5,-s9qJ7ATP7w,5,vision,8.561003,192,43,43,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__5.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/4,-s9qJ7ATP7w,4,text,4.427018,768,9,9,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__4.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/4,-s9qJ7ATP7w,4,audio,4.427018,25,420,420,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__4.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/4,-s9qJ7ATP7w,4,vision,4.427018,192,22,22,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__4.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/7,-s9qJ7ATP7w,7,text,6.966016,768,28,28,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__7.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/7,-s9qJ7ATP7w,7,audio,6.966016,25,679,679,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__7.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/7,-s9qJ7ATP7w,7,vision,6.966016,192,35,35,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__7.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/6,-s9qJ7ATP7w,6,text,2.475,768,5,5,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__6.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/6,-s9qJ7ATP7w,6,audio,2.475,25,227,227,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__6.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/6,-s9qJ7ATP7w,6,vision,2.475,192,12,12,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__6.npz,ok,{},[]
|
||||
-s9qJ7ATP7w/8,-s9qJ7ATP7w,8,text,3.294987,768,13,12,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__8.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-s9qJ7ATP7w/8,-s9qJ7ATP7w,8,audio,3.294987,25,314,314,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__8.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-s9qJ7ATP7w/8,-s9qJ7ATP7w,8,vision,3.294987,192,17,17,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-s9qJ7ATP7w__8.npz,ok_with_warning,{},"[""ctc_words_fallback:1""]"
|
||||
-yRb-Jum7EQ/1,-yRb-Jum7EQ,1,text,29.288021,768,49,49,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__1.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/1,-yRb-Jum7EQ,1,audio,29.288021,25,2906,2906,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__1.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/1,-yRb-Jum7EQ,1,vision,29.288021,192,146,146,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__1.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/5,-yRb-Jum7EQ,5,text,13.16901,768,25,25,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__5.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/5,-yRb-Jum7EQ,5,audio,13.16901,25,1300,1300,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__5.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/5,-yRb-Jum7EQ,5,vision,13.16901,192,66,66,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__5.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/6,-yRb-Jum7EQ,6,text,11.241995,768,19,19,no on-disk padding; per-sample variable length,transcript word,seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__6.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/6,-yRb-Jum7EQ,6,audio,11.241995,25,1120,1120,no on-disk padding; per-sample variable length,eGeMAPSv02 LLD frame (~10 ms),seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__6.npz,ok,{},[]
|
||||
-yRb-Jum7EQ/6,-yRb-Jum7EQ,6,vision,11.241995,192,56,56,no on-disk padding; per-sample variable length,"sampled frame (5 fps), ViT CLS; optional 52-d face blendshape",seconds from clip start; text tokens map to word_intervals_s,outputs/q1_features/features/-yRb-Jum7EQ__6.npz,ok,{},[]
|
||||
|
@@ -0,0 +1,92 @@
|
||||
{
|
||||
"created_at_utc": "2026-09-23T08:18:05.297603+00:00",
|
||||
"command": [
|
||||
"/home/gloamxun/modeling_zhaocui/Q1/q1/extract_features.py",
|
||||
"--output-dir",
|
||||
"outputs/q1_features",
|
||||
"--resume"
|
||||
],
|
||||
"python": "3.14.7 (main, Aug 10 2026, 00:00:00) [GCC 16.1.1 20260515 (Red Hat 16.1.1-2)]",
|
||||
"platform": "Linux-6.6.87.2-microsoft-standard-WSL2-x86_64-with-glibc2.43",
|
||||
"uv_version": "uv 0.11.28 (x86_64-unknown-linux-gnu)",
|
||||
"device": "cuda",
|
||||
"cuda_available": true,
|
||||
"torch_cuda_build": "13.0",
|
||||
"cudnn_version": 92400,
|
||||
"gpu_name": "NVIDIA GeForce RTX 5070 Ti",
|
||||
"external_tools": {
|
||||
"ffmpeg": "ffmpeg version 8.1.2 Copyright (c) 2000-2026 the FFmpeg developers",
|
||||
"ffprobe": "ffprobe version 8.1.2 Copyright (c) 2007-2026 the FFmpeg developers"
|
||||
},
|
||||
"package_versions": {
|
||||
"torch": "2.14.0+cu130",
|
||||
"torchvision": "0.29.0",
|
||||
"transformers": "5.17.0",
|
||||
"tokenizers": "0.23.2",
|
||||
"mediapipe": "1.0.1",
|
||||
"opencv-python-headless": "5.0.0.93",
|
||||
"opensmile": "2.6.0",
|
||||
"numpy": "2.5.2",
|
||||
"soundfile": "0.14.0",
|
||||
"openpyxl": "3.1.5",
|
||||
"matplotlib": "3.11.2",
|
||||
"Pillow": "12.3.0"
|
||||
},
|
||||
"models": {
|
||||
"text": {
|
||||
"id": "google-bert/bert-base-uncased",
|
||||
"revision": "86b5e0934494bd15c9632b12f734a8a67f723594",
|
||||
"representation": "mean of final-layer BERT subtokens per supplied whitespace token"
|
||||
},
|
||||
"forced_alignment": {
|
||||
"id": "facebook/wav2vec2-base-960h",
|
||||
"revision": "22aad52d435eb6dbaf354bdad9b0da84ce7d6156",
|
||||
"algorithm": "CTC Viterbi over supplied transcript; clip-relative seconds"
|
||||
},
|
||||
"audio": {
|
||||
"set": "eGeMAPSv02",
|
||||
"level": "LowLevelDescriptors",
|
||||
"sample_rate_hz": 16000
|
||||
},
|
||||
"vision": {
|
||||
"model": "facebook/deit-tiny-patch16-224",
|
||||
"revision": "b3428f18dcc7b543470d07f14b4a4157815d1880",
|
||||
"representation": "DeiT final-layer CLS embedding for every sampled frame",
|
||||
"sample_rate_fps": 5.0,
|
||||
"supplemental_face_feature": "MediaPipe Face Landmarker 52 blendshape scores with face_blendshape_valid mask"
|
||||
}
|
||||
},
|
||||
"alignment": {
|
||||
"granularity": "word-level",
|
||||
"primary_rule": "forced CTC transcript word intervals; mean Audio LLD and DeiT frame embeddings inside interval",
|
||||
"empty_window_rule": "nearest valid source frame; fallback flags are retained in NPZ",
|
||||
"missing_face_rule": "DeiT frame embeddings remain valid; face blendshapes are zero with face_blendshape_valid=false",
|
||||
"storage": "compressed NPZ; values float16, times float32, masks bool; no padding in per-sample files"
|
||||
},
|
||||
"face_landmarker_asset": {
|
||||
"path": "/home/gloamxun/modeling_zhaocui/Q1/models/face_landmarker.task",
|
||||
"sha256": "64184e229b263107bc2b804c6625db1341ff2bb731874b0bcc2fe6544e0bc9ff",
|
||||
"size_bytes": 3758596
|
||||
},
|
||||
"inputs": {
|
||||
"video_root": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条",
|
||||
"label_file": "/home/gloamxun/modeling_zhaocui/E题数据/附件1-数据集原始多模态样本/MOSEI数据集部分原始视频-100条/label-100.xlsx",
|
||||
"label_sha256": "827334f782b1f242c84ad944a657bc7f7c63643f71ae9c977811a3eecdd3ab33"
|
||||
},
|
||||
"outputs": {
|
||||
"feature_dir": "outputs/q1_features/features",
|
||||
"summary": "outputs/q1_features/reports/feature_summary_100x3.csv",
|
||||
"sample_table": "outputs/q1_features/reports/sample_summary.csv",
|
||||
"sample_log": "outputs/q1_features/logs/samples.jsonl"
|
||||
},
|
||||
"requested_sample_range": {
|
||||
"start": 0,
|
||||
"limit": null,
|
||||
"selected_count": 100
|
||||
},
|
||||
"completed_count": 100,
|
||||
"sample_errors": 0,
|
||||
"sample_warnings": 22,
|
||||
"aggregate_feature_bytes": 9261634,
|
||||
"typical_sample_id": "-tPCytz4rww/12"
|
||||
}
|
||||
@@ -0,0 +1,101 @@
|
||||
sample_id,video_id,clip_id,duration_s,word_count,word_alignment_valid_count,text_feature_dim,audio_raw_length,audio_valid_length,audio_feature_dim,vision_raw_length,vision_valid_length,vision_feature_dim,face_blendshape_valid_length,face_blendshape_feature_dim,ctc_inference_succeeded,alignment_granularity,feature_file,feature_file_bytes,errors,warnings
|
||||
-3g5yACwYnA/13,-3g5yACwYnA,13,5.513997,15,15,768,535,535,25,28,28,192,28,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-3g5yACwYnA__13.npz,70429,{},[]
|
||||
-3g5yACwYnA/3,-3g5yACwYnA,3,14.388997,29,29,768,1428,1428,25,72,72,192,72,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-3g5yACwYnA__3.npz,153606,{},[]
|
||||
-3g5yACwYnA/2,-3g5yACwYnA,2,9.39401,14,14,768,919,919,25,47,47,192,47,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-3g5yACwYnA__2.npz,93925,{},[]
|
||||
-3g5yACwYnA/9,-3g5yACwYnA,9,8.816992,21,21,768,865,865,25,44,44,192,44,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-3g5yACwYnA__9.npz,104222,{},[]
|
||||
-3nNcZdcdvU/5,-3nNcZdcdvU,5,7.867969,18,18,768,774,774,25,40,40,192,40,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-3nNcZdcdvU__5.npz,92502,{},[]
|
||||
-HwX2H8Z4hY/2,-HwX2H8Z4hY,2,3.982031,8,7,768,387,387,25,20,20,192,4,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-HwX2H8Z4hY__2.npz,44625,{},['ctc_words_fallback:1']
|
||||
-HwX2H8Z4hY/5,-HwX2H8Z4hY,5,5.652995,10,9,768,550,550,25,28,28,192,7,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-HwX2H8Z4hY__5.npz,60515,{},['ctc_words_fallback:1']
|
||||
-HwX2H8Z4hY/6,-HwX2H8Z4hY,6,3.358008,7,7,768,321,321,25,17,17,192,8,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-HwX2H8Z4hY__6.npz,40308,{},[]
|
||||
-HwX2H8Z4hY/9,-HwX2H8Z4hY,9,7.733984,22,22,768,759,759,25,39,39,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-HwX2H8Z4hY__9.npz,94012,{},['no_face_blendshapes_detected']
|
||||
-NFrJFQijFE/1,-NFrJFQijFE,1,5.746,16,16,768,561,561,25,29,29,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-NFrJFQijFE__1.npz,65573,{},['no_face_blendshapes_detected']
|
||||
-NFrJFQijFE/2,-NFrJFQijFE,2,6.856,18,18,768,665,665,25,34,34,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-NFrJFQijFE__2.npz,74682,{},['no_face_blendshapes_detected']
|
||||
-THoVjtIkeU/12,-THoVjtIkeU,12,14.896029,39,39,768,1476,1476,25,75,75,192,75,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-THoVjtIkeU__12.npz,175729,{},[]
|
||||
-THoVjtIkeU/2,-THoVjtIkeU,2,4.291992,10,10,768,419,419,25,22,22,192,22,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-THoVjtIkeU__2.npz,54279,{},[]
|
||||
-THoVjtIkeU/6,-THoVjtIkeU,6,8.097005,30,30,768,794,794,25,41,41,192,41,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-THoVjtIkeU__6.npz,116720,{},[]
|
||||
-UuX1xuaiiE/1,-UuX1xuaiiE,1,10.35,27,27,768,1022,1022,25,52,52,192,2,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UuX1xuaiiE__1.npz,117161,{},[]
|
||||
-UuX1xuaiiE/0,-UuX1xuaiiE,0,3.633333,9,9,768,353,353,25,19,19,192,9,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UuX1xuaiiE__0.npz,47230,{},[]
|
||||
-UuX1xuaiiE/3,-UuX1xuaiiE,3,4.130013,9,9,768,399,399,25,21,21,192,20,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UuX1xuaiiE__3.npz,51645,{},[]
|
||||
-UuX1xuaiiE/6,-UuX1xuaiiE,6,8.113997,22,22,768,790,790,25,40,40,192,39,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UuX1xuaiiE__6.npz,100158,{},[]
|
||||
-a55Q6RWvTA/3,-a55Q6RWvTA,3,22.153971,65,65,768,2204,2204,25,111,111,192,111,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-a55Q6RWvTA__3.npz,275958,{},[]
|
||||
-aNfi7CP8vM/7,-aNfi7CP8vM,7,8.694987,18,18,768,849,849,25,43,43,192,43,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-aNfi7CP8vM__7.npz,98603,{},[]
|
||||
-aqamKhZ1Ec/0,-aqamKhZ1Ec,0,10.966667,14,13,768,1085,1085,25,55,55,192,55,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-aqamKhZ1Ec__0.npz,101705,{},['ctc_words_fallback:1']
|
||||
-dxfTGcXJoc/1,-dxfTGcXJoc,1,16.161003,36,36,768,1597,1597,25,81,81,192,81,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-dxfTGcXJoc__1.npz,180363,{},[]
|
||||
-dxfTGcXJoc/0,-dxfTGcXJoc,0,20.5,41,38,768,2037,2037,25,103,103,192,80,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-dxfTGcXJoc__0.npz,202759,{},['ctc_words_fallback:3']
|
||||
-dxfTGcXJoc/2,-dxfTGcXJoc,2,16.697982,34,32,768,1659,1659,25,84,84,192,84,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-dxfTGcXJoc__2.npz,180106,{},['ctc_words_fallback:2']
|
||||
-dxfTGcXJoc/6,-dxfTGcXJoc,6,12.735026,27,27,768,1258,1258,25,64,64,192,63,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-dxfTGcXJoc__6.npz,140160,{},[]
|
||||
-egA8-b7-3M/26,-egA8-b7-3M,26,6.03099,15,15,768,588,588,25,30,30,192,30,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__26.npz,75011,{},[]
|
||||
-egA8-b7-3M/17,-egA8-b7-3M,17,7.271029,16,16,768,705,705,25,36,36,192,36,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__17.npz,84195,{},[]
|
||||
-egA8-b7-3M/18,-egA8-b7-3M,18,8.386003,22,22,768,822,822,25,42,42,192,42,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__18.npz,103490,{},[]
|
||||
-egA8-b7-3M/16,-egA8-b7-3M,16,5.538021,11,11,768,544,544,25,28,28,192,28,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__16.npz,64870,{},[]
|
||||
-egA8-b7-3M/13,-egA8-b7-3M,13,4.183984,11,11,768,398,398,25,21,21,192,21,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__13.npz,55221,{},[]
|
||||
-egA8-b7-3M/1,-egA8-b7-3M,1,10.266016,20,19,768,1011,1011,25,51,51,192,51,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__1.npz,112851,{},['ctc_words_fallback:1']
|
||||
-egA8-b7-3M/6,-egA8-b7-3M,6,6.264974,12,12,768,614,614,25,32,32,192,32,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__6.npz,71552,{},[]
|
||||
-egA8-b7-3M/9,-egA8-b7-3M,9,5.089974,10,10,768,489,489,25,25,25,192,25,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__9.npz,59194,{},[]
|
||||
-egA8-b7-3M/20,-egA8-b7-3M,20,6.644987,20,20,768,643,643,25,33,33,192,33,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-egA8-b7-3M__20.npz,87987,{},[]
|
||||
-iRBcNs9oI8/3,-iRBcNs9oI8,3,5.621,8,8,768,549,549,25,28,28,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-iRBcNs9oI8__3.npz,55728,{},['no_face_blendshapes_detected']
|
||||
-iRBcNs9oI8/7,-iRBcNs9oI8,7,4.104,9,9,768,396,396,25,20,20,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-iRBcNs9oI8__7.npz,48402,{},['no_face_blendshapes_detected']
|
||||
-iRBcNs9oI8/6,-iRBcNs9oI8,6,2.903,5,5,768,278,278,25,15,15,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-iRBcNs9oI8__6.npz,34247,{},['no_face_blendshapes_detected']
|
||||
-iRBcNs9oI8/9,-iRBcNs9oI8,9,3.416,5,5,768,333,333,25,17,17,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-iRBcNs9oI8__9.npz,36025,{},['no_face_blendshapes_detected']
|
||||
-iRBcNs9oI8/8,-iRBcNs9oI8,8,8.093,21,21,768,798,798,25,41,41,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-iRBcNs9oI8__8.npz,94217,{},['no_face_blendshapes_detected']
|
||||
-lzEya4AM_4/5,-lzEya4AM_4,5,7.675,19,19,768,752,752,25,39,39,192,39,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-lzEya4AM_4__5.npz,92703,{},[]
|
||||
-lzEya4AM_4/6,-lzEya4AM_4,6,14.791992,43,43,768,1470,1470,25,74,74,192,74,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-lzEya4AM_4__6.npz,184072,{},[]
|
||||
-mJ2ud6oKI8/1,-mJ2ud6oKI8,1,6.103,13,13,768,601,601,25,31,31,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mJ2ud6oKI8__1.npz,42496,{},['no_face_blendshapes_detected']
|
||||
-mJ2ud6oKI8/2,-mJ2ud6oKI8,2,5.731,11,11,768,566,566,25,29,29,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mJ2ud6oKI8__2.npz,38780,{},['no_face_blendshapes_detected']
|
||||
-mJ2ud6oKI8/6,-mJ2ud6oKI8,6,2.257,5,5,768,218,218,25,12,12,192,12,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mJ2ud6oKI8__6.npz,31649,{},[]
|
||||
-mJ2ud6oKI8/9,-mJ2ud6oKI8,9,7.033,22,22,768,686,686,25,35,35,192,34,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mJ2ud6oKI8__9.npz,91413,{},[]
|
||||
-mJ2ud6oKI8/8,-mJ2ud6oKI8,8,4.192,11,11,768,413,413,25,21,21,192,21,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mJ2ud6oKI8__8.npz,55199,{},[]
|
||||
-mqbVkbCndg/0,-mqbVkbCndg,0,6.466667,12,12,768,634,634,25,33,33,192,33,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-mqbVkbCndg__0.npz,72269,{},[]
|
||||
-t217m2on-s/2,-t217m2on-s,2,5.686003,12,12,768,559,559,25,29,29,192,29,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-t217m2on-s__2.npz,67378,{},[]
|
||||
-t217m2on-s/7,-t217m2on-s,7,17.183008,45,45,768,1698,1698,25,86,86,192,86,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-t217m2on-s__7.npz,203231,{},[]
|
||||
-tANM6ETl_M/3,-tANM6ETl_M,3,6.758008,22,22,768,656,656,25,34,34,192,34,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tANM6ETl_M__3.npz,93347,{},[]
|
||||
-tPCytz4rww/11,-tPCytz4rww,11,5.466992,17,17,768,533,533,25,28,28,192,28,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tPCytz4rww__11.npz,76420,{},[]
|
||||
-tPCytz4rww/10,-tPCytz4rww,10,4.788997,12,12,768,463,463,25,24,24,192,24,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tPCytz4rww__10.npz,60662,{},[]
|
||||
-tPCytz4rww/12,-tPCytz4rww,12,11.863997,26,26,768,1169,1169,25,59,59,192,59,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tPCytz4rww__12.npz,133451,{},[]
|
||||
-tPCytz4rww/16,-tPCytz4rww,16,7.20599,16,16,768,709,709,25,36,36,192,36,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tPCytz4rww__16.npz,83725,{},[]
|
||||
-tPCytz4rww/18,-tPCytz4rww,18,6.644987,16,16,768,652,652,25,34,34,192,34,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-tPCytz4rww__18.npz,81628,{},[]
|
||||
-vxjVxOeScU/4,-vxjVxOeScU,4,9.127018,21,21,768,899,899,25,46,46,192,46,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-vxjVxOeScU__4.npz,109211,{},[]
|
||||
-wMB_hJL-3o/7,-wMB_hJL-3o,7,6.04401,22,22,768,593,593,25,31,31,192,31,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wMB_hJL-3o__7.npz,87786,{},[]
|
||||
-wny0OAz3g8/1,-wny0OAz3g8,1,6.84401,23,22,768,673,673,25,35,35,192,14,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__1.npz,94004,{},['ctc_words_fallback:1']
|
||||
-wny0OAz3g8/0,-wny0OAz3g8,0,3.333333,9,9,768,323,323,25,17,17,192,14,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__0.npz,46886,{},[]
|
||||
-wny0OAz3g8/3,-wny0OAz3g8,3,6.146029,20,20,768,605,605,25,31,31,192,8,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__3.npz,84176,{},[]
|
||||
-wny0OAz3g8/2,-wny0OAz3g8,2,6.686979,23,23,768,648,648,25,33,33,192,27,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__2.npz,89372,{},[]
|
||||
-wny0OAz3g8/5,-wny0OAz3g8,5,6.911979,20,20,768,670,670,25,34,34,192,6,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__5.npz,86434,{},[]
|
||||
-wny0OAz3g8/7,-wny0OAz3g8,7,8.067969,29,29,768,787,787,25,40,40,192,35,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__7.npz,115720,{},[]
|
||||
-wny0OAz3g8/9,-wny0OAz3g8,9,6.213021,20,20,768,600,600,25,31,31,192,29,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-wny0OAz3g8__9.npz,86748,{},[]
|
||||
-571d8cVauQ/0,-571d8cVauQ,0,5.066667,12,12,768,495,495,25,26,26,192,25,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-571d8cVauQ__0.npz,58874,{},[]
|
||||
-571d8cVauQ/5,-571d8cVauQ,5,15.272982,43,43,768,1507,1507,25,76,76,192,76,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-571d8cVauQ__5.npz,186922,{},[]
|
||||
-I_e4mIh0yE/1,-I_e4mIh0yE,1,7.622005,18,18,768,740,740,25,38,38,192,38,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-I_e4mIh0yE__1.npz,89671,{},[]
|
||||
-I_e4mIh0yE/3,-I_e4mIh0yE,3,9.163021,22,22,768,895,895,25,46,46,192,46,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-I_e4mIh0yE__3.npz,106161,{},[]
|
||||
-UacrmKiTn4/10,-UacrmKiTn4,10,7.361979,18,18,768,720,720,25,37,37,192,37,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UacrmKiTn4__10.npz,90141,{},[]
|
||||
-UacrmKiTn4/4,-UacrmKiTn4,4,4.741016,14,14,768,464,464,25,24,24,192,24,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UacrmKiTn4__4.npz,64832,{},[]
|
||||
-hnBHBN8p5A/7,-hnBHBN8p5A,7,7.372,13,13,768,726,726,25,36,36,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-hnBHBN8p5A__7.npz,72066,{},['no_face_blendshapes_detected']
|
||||
-hnBHBN8p5A/6,-hnBHBN8p5A,6,6.401,13,13,768,629,629,25,31,31,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-hnBHBN8p5A__6.npz,65954,{},['no_face_blendshapes_detected']
|
||||
-qDkUB0GgYY/6,-qDkUB0GgYY,6,4.677995,16,16,768,457,457,25,24,24,192,24,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-qDkUB0GgYY__6.npz,69147,{},[]
|
||||
-uywlfIYOS8/4,-uywlfIYOS8,4,6.044987,18,18,768,584,584,25,30,30,192,30,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-uywlfIYOS8__4.npz,80911,{},[]
|
||||
-6rXp3zJ3kc/8,-6rXp3zJ3kc,8,12.805013,34,34,768,1269,1269,25,64,64,192,64,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-6rXp3zJ3kc__8.npz,155936,{},[]
|
||||
-9y-fZ3swSY/0,-9y-fZ3swSY,0,6.833333,22,22,768,671,671,25,35,35,192,35,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-9y-fZ3swSY__0.npz,95005,{},[]
|
||||
-9y-fZ3swSY/4,-9y-fZ3swSY,4,2.821029,9,9,768,262,262,25,14,14,192,13,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-9y-fZ3swSY__4.npz,39524,{},[]
|
||||
-9y-fZ3swSY/8,-9y-fZ3swSY,8,4.988997,12,12,768,487,487,25,25,25,192,18,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-9y-fZ3swSY__8.npz,61536,{},[]
|
||||
-AUZQgSxyPQ/2,-AUZQgSxyPQ,2,22.511003,41,41,768,2236,2236,25,113,113,192,113,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-AUZQgSxyPQ__2.npz,221014,{},[]
|
||||
-HeZS2-Prhc/2,-HeZS2-Prhc,2,8.261979,16,16,768,811,811,25,41,41,192,41,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-HeZS2-Prhc__2.npz,91019,{},[]
|
||||
-MeTTeMJBNc/0,-MeTTeMJBNc,0,9.3,21,21,768,917,917,25,47,47,192,46,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-MeTTeMJBNc__0.npz,100330,{},[]
|
||||
-MeTTeMJBNc/13,-MeTTeMJBNc,13,5.430013,14,14,768,521,521,25,27,27,192,27,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-MeTTeMJBNc__13.npz,66667,{},[]
|
||||
-MeTTeMJBNc/7,-MeTTeMJBNc,7,10.516992,31,31,768,1037,1037,25,53,53,192,53,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-MeTTeMJBNc__7.npz,134532,{},[]
|
||||
-RfYyzHpjk4/11,-RfYyzHpjk4,11,5.238997,17,17,768,503,503,25,26,26,192,26,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-RfYyzHpjk4__11.npz,73768,{},[]
|
||||
-RfYyzHpjk4/8,-RfYyzHpjk4,8,4.588997,17,17,768,449,449,25,23,23,192,23,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-RfYyzHpjk4__8.npz,69862,{},[]
|
||||
-RfYyzHpjk4/2,-RfYyzHpjk4,2,5.516016,25,25,768,535,535,25,28,28,192,27,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-RfYyzHpjk4__2.npz,84993,{},[]
|
||||
-UUCSKoHeMA/0,-UUCSKoHeMA,0,7.8,18,18,768,769,769,25,39,39,192,38,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-UUCSKoHeMA__0.npz,86051,{},[]
|
||||
-ri04Z7vwnc/0,-ri04Z7vwnc,0,2.807,8,8,768,272,272,25,14,14,192,0,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-ri04Z7vwnc__0.npz,39930,{},['no_face_blendshapes_detected']
|
||||
-ri04Z7vwnc/2,-ri04Z7vwnc,2,6.027,16,16,768,587,587,25,29,29,192,10,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-ri04Z7vwnc__2.npz,73850,{},[]
|
||||
-ri04Z7vwnc/5,-ri04Z7vwnc,5,3.545,9,8,768,339,339,25,17,17,192,17,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-ri04Z7vwnc__5.npz,47804,{},['ctc_words_fallback:1']
|
||||
-s9qJ7ATP7w/1,-s9qJ7ATP7w,1,4.791992,11,11,768,460,460,25,24,24,192,24,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__1.npz,58350,{},[]
|
||||
-s9qJ7ATP7w/0,-s9qJ7ATP7w,0,6.8,24,24,768,667,667,25,34,34,192,31,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__0.npz,96329,{},[]
|
||||
-s9qJ7ATP7w/5,-s9qJ7ATP7w,5,8.561003,19,19,768,835,835,25,43,43,192,43,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__5.npz,99292,{},[]
|
||||
-s9qJ7ATP7w/4,-s9qJ7ATP7w,4,4.427018,9,9,768,420,420,25,22,22,192,15,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__4.npz,51817,{},[]
|
||||
-s9qJ7ATP7w/7,-s9qJ7ATP7w,7,6.966016,28,28,768,679,679,25,35,35,192,20,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__7.npz,101098,{},[]
|
||||
-s9qJ7ATP7w/6,-s9qJ7ATP7w,6,2.475,5,5,768,227,227,25,12,12,192,10,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__6.npz,30573,{},[]
|
||||
-s9qJ7ATP7w/8,-s9qJ7ATP7w,8,3.294987,13,12,768,314,314,25,17,17,192,15,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-s9qJ7ATP7w__8.npz,52875,{},['ctc_words_fallback:1']
|
||||
-yRb-Jum7EQ/1,-yRb-Jum7EQ,1,29.288021,49,49,768,2906,2906,25,146,146,192,136,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-yRb-Jum7EQ__1.npz,263653,{},[]
|
||||
-yRb-Jum7EQ/5,-yRb-Jum7EQ,5,13.16901,25,25,768,1300,1300,25,66,66,192,66,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-yRb-Jum7EQ__5.npz,139890,{},[]
|
||||
-yRb-Jum7EQ/6,-yRb-Jum7EQ,6,11.241995,19,19,768,1120,1120,25,56,56,192,56,52,True,transcript word; Audio/Vision pooled over forced CTC word interval,outputs/q1_features/features/-yRb-Jum7EQ__6.npz,112532,{},[]
|
||||
|
Binary file not shown.
|
After Width: | Height: | Size: 901 KiB |
Reference in New Issue
Block a user