student / reports /benchmark_report.json
amir0907's picture
Surgical emotion module: emotion2vec_plus_base -> continuous 12.5 Hz vectors
0bb1236 verified
Raw History Blame Contribute Delete
13.7 kB
{
"gpu": "Tesla T4",
"torch": "2.11.0+cu128",
"device": "cuda:0",
"labels": [
"angry",
"disgusted",
"fearful",
"happy",
"neutral",
"other",
"sad",
"surprised",
"unk"
],
"paths": {
"teacher_pure": {
"mean_ms_per_utt": 33.314667375066165,
"rtf_mean": 0.009350432942505241,
"utt_per_s": 30.01680877499723,
"audio_x_realtime": 147.63716481204952
},
"student_total": {
"mean_ms_per_utt": 34.070405125059246,
"rtf_mean": 0.00955089521538932,
"utt_per_s": 29.35098647431364,
"audio_x_realtime": 142.4254284250466
},
"adapter_only": {
"mean_ms_per_utt": 2.6908564998772513,
"rtf_mean": 0.0007417373249696411,
"utt_per_s": 371.6288847233648,
"audio_x_realtime": 1371.339065435046
},
"teacher_pipeline_funasr": {
"mean_ms_per_utt": 44.92722699978913,
"rtf_mean": 0.013555008051830552,
"utt_per_s": 22.258217717392032,
"audio_x_realtime": 73.77347148568855
}
},
"files": {
"03-01-01-01-01-01-19.wav": {
"emotion": "neutral",
"dur_s": 3.37,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 1.0,
"js": 6e-05,
"pooled_cos": 0.99994,
"frame_cos": 0.99981,
"intensity": {
"mean": 0.274,
"std": 0.005,
"min": 0.246,
"max": 0.279,
"corr_target": 0.376
}
},
"03-01-01-01-01-02-19.wav": {
"emotion": "neutral",
"dur_s": 3.24,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 0.998,
"js": 0.00066,
"pooled_cos": 0.99868,
"frame_cos": 0.96646,
"intensity": {
"mean": 0.176,
"std": 0.088,
"min": 0.086,
"max": 0.284,
"corr_target": 0.521
}
},
"03-01-01-01-02-01-19.wav": {
"emotion": "neutral",
"dur_s": 3.34,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 0.996,
"js": 0.00121,
"pooled_cos": 0.99929,
"frame_cos": 0.98726,
"intensity": {
"mean": 0.116,
"std": 0.056,
"min": 0.089,
"max": 0.28,
"corr_target": 0.587
}
},
"03-01-02-01-01-01-19.wav": {
"emotion": "calm",
"dur_s": 3.67,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 1.0,
"js": 5e-05,
"pooled_cos": 0.99991,
"frame_cos": 0.99989,
"intensity": {
"mean": 0.267,
"std": 0.002,
"min": 0.262,
"max": 0.269,
"corr_target": -0.213
}
},
"03-01-02-01-01-02-19.wav": {
"emotion": "calm",
"dur_s": 3.67,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 0.999,
"js": 0.00022,
"pooled_cos": 0.99964,
"frame_cos": 0.99587,
"intensity": {
"mean": 0.257,
"std": 0.042,
"min": 0.166,
"max": 0.292,
"corr_target": 0.439
}
},
"03-01-02-01-02-01-19.wav": {
"emotion": "calm",
"dur_s": 3.34,
"teacher_top": "neutral",
"teacher_p": 1.0,
"student_top": "neutral",
"student_p": 0.989,
"js": 0.00388,
"pooled_cos": 0.99692,
"frame_cos": 0.97125,
"intensity": {
"mean": 0.186,
"std": 0.08,
"min": 0.081,
"max": 0.285,
"corr_target": 0.139
}
},
"03-01-03-01-01-01-19.wav": {
"emotion": "happy",
"dur_s": 3.64,
"teacher_top": "happy",
"teacher_p": 1.0,
"student_top": "happy",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.99975,
"frame_cos": 0.99908,
"intensity": {
"mean": 0.224,
"std": 0.031,
"min": 0.133,
"max": 0.256,
"corr_target": 0.344
}
},
"03-01-03-01-01-02-19.wav": {
"emotion": "happy",
"dur_s": 3.7,
"teacher_top": "happy",
"teacher_p": 1.0,
"student_top": "happy",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.99982,
"frame_cos": 0.99966,
"intensity": {
"mean": 0.233,
"std": 0.011,
"min": 0.2,
"max": 0.261,
"corr_target": 0.281
}
},
"03-01-03-01-02-01-19.wav": {
"emotion": "happy",
"dur_s": 3.27,
"teacher_top": "happy",
"teacher_p": 1.0,
"student_top": "happy",
"student_p": 1.0,
"js": 6e-05,
"pooled_cos": 0.99951,
"frame_cos": 0.99796,
"intensity": {
"mean": 0.215,
"std": 0.061,
"min": 0.109,
"max": 0.281,
"corr_target": 0.674
}
},
"03-01-04-01-01-01-19.wav": {
"emotion": "sad",
"dur_s": 3.44,
"teacher_top": "sad",
"teacher_p": 1.0,
"student_top": "sad",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.99981,
"frame_cos": 0.99791,
"intensity": {
"mean": 0.215,
"std": 0.041,
"min": 0.117,
"max": 0.248,
"corr_target": -0.012
}
},
"03-01-04-01-01-02-19.wav": {
"emotion": "sad",
"dur_s": 3.67,
"teacher_top": "sad",
"teacher_p": 1.0,
"student_top": "sad",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.9998,
"frame_cos": 0.99912,
"intensity": {
"mean": 0.234,
"std": 0.039,
"min": 0.115,
"max": 0.261,
"corr_target": 0.361
}
},
"03-01-04-01-02-01-19.wav": {
"emotion": "sad",
"dur_s": 3.17,
"teacher_top": "sad",
"teacher_p": 1.0,
"student_top": "sad",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.99986,
"frame_cos": 0.99847,
"intensity": {
"mean": 0.228,
"std": 0.037,
"min": 0.129,
"max": 0.263,
"corr_target": -0.048
}
},
"03-01-05-01-01-01-19.wav": {
"emotion": "angry",
"dur_s": 3.77,
"teacher_top": "angry",
"teacher_p": 1.0,
"student_top": "angry",
"student_p": 1.0,
"js": 0.0,
"pooled_cos": 0.99993,
"frame_cos": 0.99987,
"intensity": {
"mean": 0.248,
"std": 0.012,
"min": 0.226,
"max": 0.267,
"corr_target": 0.737
}
},
"03-01-05-01-01-02-19.wav": {
"emotion": "angry",
"dur_s": 3.7,
"teacher_top": "angry",
"teacher_p": 1.0,
"student_top": "angry",
"student_p": 1.0,
"js": 0.0,
"pooled_cos": 0.99981,
"frame_cos": 0.99843,
"intensity": {
"mean": 0.221,
"std": 0.015,
"min": 0.139,
"max": 0.239,
"corr_target": 0.206
}
},
"03-01-05-01-02-01-19.wav": {
"emotion": "angry",
"dur_s": 3.3,
"teacher_top": "angry",
"teacher_p": 1.0,
"student_top": "angry",
"student_p": 0.999,
"js": 0.0003,
"pooled_cos": 0.99793,
"frame_cos": 0.99519,
"intensity": {
"mean": 0.171,
"std": 0.02,
"min": 0.139,
"max": 0.212,
"corr_target": 0.518
}
},
"03-01-06-01-01-01-19.wav": {
"emotion": "fearful",
"dur_s": 3.7,
"teacher_top": "fearful",
"teacher_p": 1.0,
"student_top": "fearful",
"student_p": 0.999,
"js": 0.0003,
"pooled_cos": 0.99965,
"frame_cos": 0.99905,
"intensity": {
"mean": 0.211,
"std": 0.017,
"min": 0.148,
"max": 0.237,
"corr_target": -0.27
}
},
"03-01-06-01-01-02-19.wav": {
"emotion": "fearful",
"dur_s": 3.5,
"teacher_top": "fearful",
"teacher_p": 1.0,
"student_top": "fearful",
"student_p": 0.999,
"js": 0.00017,
"pooled_cos": 0.99955,
"frame_cos": 0.99841,
"intensity": {
"mean": 0.194,
"std": 0.027,
"min": 0.119,
"max": 0.231,
"corr_target": -0.335
}
},
"03-01-06-01-02-01-19.wav": {
"emotion": "fearful",
"dur_s": 3.77,
"teacher_top": "fearful",
"teacher_p": 0.995,
"student_top": "fearful",
"student_p": 0.988,
"js": 0.0009,
"pooled_cos": 0.99938,
"frame_cos": 0.99708,
"intensity": {
"mean": 0.175,
"std": 0.028,
"min": 0.126,
"max": 0.238,
"corr_target": -0.04
}
},
"03-01-07-01-01-01-19.wav": {
"emotion": "disgust",
"dur_s": 4.3,
"teacher_top": "disgusted",
"teacher_p": 1.0,
"student_top": "disgusted",
"student_p": 1.0,
"js": 0.0,
"pooled_cos": 0.99941,
"frame_cos": 0.99938,
"intensity": {
"mean": 0.218,
"std": 0.002,
"min": 0.215,
"max": 0.223,
"corr_target": 0.41
}
},
"03-01-07-01-01-02-19.wav": {
"emotion": "disgust",
"dur_s": 4.84,
"teacher_top": "disgusted",
"teacher_p": 1.0,
"student_top": "disgusted",
"student_p": 1.0,
"js": 0.0,
"pooled_cos": 0.99932,
"frame_cos": 0.99929,
"intensity": {
"mean": 0.211,
"std": 0.002,
"min": 0.208,
"max": 0.216,
"corr_target": 0.144
}
},
"03-01-07-01-02-01-19.wav": {
"emotion": "disgust",
"dur_s": 4.17,
"teacher_top": "disgusted",
"teacher_p": 1.0,
"student_top": "disgusted",
"student_p": 1.0,
"js": 0.0,
"pooled_cos": 0.99944,
"frame_cos": 0.99941,
"intensity": {
"mean": 0.22,
"std": 0.001,
"min": 0.217,
"max": 0.223,
"corr_target": 0.504
}
},
"03-01-08-01-01-01-19.wav": {
"emotion": "surprised",
"dur_s": 3.74,
"teacher_top": "surprised",
"teacher_p": 1.0,
"student_top": "surprised",
"student_p": 1.0,
"js": 3e-05,
"pooled_cos": 0.99886,
"frame_cos": 0.99732,
"intensity": {
"mean": 0.193,
"std": 0.03,
"min": 0.14,
"max": 0.252,
"corr_target": 0.546
}
},
"03-01-08-01-01-02-19.wav": {
"emotion": "surprised",
"dur_s": 3.54,
"teacher_top": "surprised",
"teacher_p": 1.0,
"student_top": "surprised",
"student_p": 1.0,
"js": 1e-05,
"pooled_cos": 0.9993,
"frame_cos": 0.99885,
"intensity": {
"mean": 0.203,
"std": 0.019,
"min": 0.16,
"max": 0.239,
"corr_target": 0.206
}
},
"03-01-08-01-02-01-19.wav": {
"emotion": "surprised",
"dur_s": 4.1,
"teacher_top": "surprised",
"teacher_p": 1.0,
"student_top": "surprised",
"student_p": 1.0,
"js": 3e-05,
"pooled_cos": 0.99926,
"frame_cos": 0.99881,
"intensity": {
"mean": 0.234,
"std": 0.021,
"min": 0.186,
"max": 0.286,
"corr_target": 0.42
}
}
},
"scaling": {
"duration": {
"1s": {
"dur_s": 1,
"teacher_pure": {
"mean_ms": 11.553318900041631,
"std_ms": 0.09967757742976557,
"min_ms": 11.37084899983165,
"rtf": 0.011553318900041631
},
"student_total": {
"mean_ms": 14.404504100093618,
"std_ms": 0.17700507011417319,
"min_ms": 14.133429999674263,
"rtf": 0.014404504100093618
},
"adapter_only": {
"mean_ms": 2.732756299974426,
"std_ms": 0.18999702998665344,
"min_ms": 2.5520230001347954,
"rtf": 0.0027327562999744258
}
},
"2s": {
"dur_s": 2,
"teacher_pure": {
"mean_ms": 15.61593050009833,
"std_ms": 0.6203670067385955,
"min_ms": 14.095423000071605,
"rtf": 0.007807965250049165
},
"student_total": {
"mean_ms": 17.062608400010504,
"std_ms": 0.23768206298814967,
"min_ms": 16.811338000479736,
"rtf": 0.008531304200005252
},
"adapter_only": {
"mean_ms": 2.705648499977542,
"std_ms": 0.09339262221847873,
"min_ms": 2.617109000311757,
"rtf": 0.001352824249988771
}
},
"3s": {
"dur_s": 3,
"teacher_pure": {
"mean_ms": 22.21067629998288,
"std_ms": 1.0634458338704,
"min_ms": 21.050155000011728,
"rtf": 0.007403558766660959
},
"student_total": {
"mean_ms": 22.776801099917066,
"std_ms": 0.5247787067995497,
"min_ms": 21.94516700001259,
"rtf": 0.007592267033305689
},
"adapter_only": {
"mean_ms": 2.5522279999677266,
"std_ms": 0.028036102248190167,
"min_ms": 2.514337999855343,
"rtf": 0.0008507426666559088
}
},
"4s": {
"dur_s": 4,
"teacher_pure": {
"mean_ms": 27.72835359992314,
"std_ms": 0.7865264136788663,
"min_ms": 27.01051100029872,
"rtf": 0.006932088399980785
},
"student_total": {
"mean_ms": 29.05509339980199,
"std_ms": 0.5382824371866328,
"min_ms": 28.091340999708336,
"rtf": 0.007263773349950498
},
"adapter_only": {
"mean_ms": 2.549557800102775,
"std_ms": 0.08122501979887602,
"min_ms": 2.484499000274809,
"rtf": 0.0006373894500256938
}
},
"10s": {
"dur_s": 10,
"teacher_pure": {
"mean_ms": 68.44333810004173,
"std_ms": 0.9847013292069681,
"min_ms": 66.79080899994005,
"rtf": 0.006844333810004173
},
"student_total": {
"mean_ms": 70.42835050006033,
"std_ms": 1.2389065947566182,
"min_ms": 68.41233399973135,
"rtf": 0.007042835050006033
},
"adapter_only": {
"mean_ms": 2.5619056999858003,
"std_ms": 0.0661319298171018,
"min_ms": 2.5126059999820427,
"rtf": 0.00025619056999858
}
}
},
"adapter_batch": {
"B1": {
"mean_ms": 2.5623809999160585,
"std_ms": 0.046981332240909765,
"min_ms": 2.5086689993258915,
"utt_per_s": 390.262025839545
},
"B4": {
"mean_ms": 2.6514930999837816,
"std_ms": 0.11163035081893366,
"min_ms": 2.4829180001688655,
"utt_per_s": 1508.5839748270387
},
"B8": {
"mean_ms": 3.340361800019309,
"std_ms": 0.33785645295285227,
"min_ms": 3.064344000449637,
"utt_per_s": 2394.950151793065
}
},
"student_fp16_autocast_3s": {
"mean_ms": 17.815138100104377,
"std_ms": 0.47245930490302995,
"min_ms": 17.379814999912924
},
"cpu_3s": {
"student_total": {
"mean_ms": 300.41210733331053,
"std_ms": 6.854120615983172,
"min_ms": 290.76308000003337
}
}
},
"quality_summary": {
"n_files": 24,
"top1_agreement": 1.0,
"mean_js": 0.00033086610305114544,
"mean_pooled_cos": 0.9993650789062182,
"mean_frame_cos": 0.9955763841668764,
"mean_intensity_corr": 0.2705703211160692
},
"params": {
"teacher_backbone": 93797909,
"student_adapter": 3180811,
"adapter_overhead_pct": 3.391132098691027
},
"memory": {
"peak_gpu_allocated_mb": 625.831936,
"peak_gpu_reserved_mb": 1004.535808
}
}