|
|
|
@@ -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,{},[]
|
