vital-decoder-v1-v7 / evaluation /test_eval.json
duckking032's picture
Publish V7 standalone codebook decoder
85e7a47 verified
Raw
History Blame Contribute Delete
9 kB
{
"checkpoint": "/workspace/checkpoints/decoder_v1_v7_soft/step_00001000.pt",
"step": 1000,
"test_items": 3540,
"active_control_mae": 0.21187633275985718,
"activity_accuracy": 0.805084764957428,
"mean_control_correlation": 0.12764105139067397,
"mean_acoustic_correlation": 0.8683784763018291,
"asset_accuracy": 0.18276835978031158,
"controls": {
"osc_1_on": {
"active_count": 3540,
"mae": 0.07509277015924454,
"correlation": 0.027110153809189796,
"activity_accuracy": 1.0
},
"osc_1_level": {
"active_count": 3313,
"mae": 0.2022600620985031,
"correlation": 0.18604996800422668,
"activity_accuracy": 0.9358757138252258
},
"osc_1_wave_frame": {
"active_count": 3313,
"mae": 0.20737269520759583,
"correlation": 0.08357028663158417,
"activity_accuracy": 0.9358757138252258
},
"osc_1_spectral_morph": {
"active_count": 3313,
"mae": 0.13070207834243774,
"correlation": -0.030574321746826172,
"activity_accuracy": 0.9358757138252258
},
"osc_1_unison_detune": {
"active_count": 1862,
"mae": 0.11004240065813065,
"correlation": 0.1938508301973343,
"activity_accuracy": 0.6022598743438721
},
"osc_1_unison_blend": {
"active_count": 1862,
"mae": 0.0472741574048996,
"correlation": -0.06401322036981583,
"activity_accuracy": 0.5966101884841919
},
"osc_2_on": {
"active_count": 3540,
"mae": 0.1894226372241974,
"correlation": 0.02760283648967743,
"activity_accuracy": 1.0
},
"osc_2_level": {
"active_count": 2904,
"mae": 0.26495280861854553,
"correlation": 0.1757328063249588,
"activity_accuracy": 0.8274011015892029
},
"osc_2_wave_frame": {
"active_count": 2904,
"mae": 0.2672661244869232,
"correlation": 0.07045401632785797,
"activity_accuracy": 0.8274011015892029
},
"osc_2_spectral_morph": {
"active_count": 2904,
"mae": 0.12785618007183075,
"correlation": 0.05788930878043175,
"activity_accuracy": 0.8262711763381958
},
"osc_2_unison_detune": {
"active_count": 1663,
"mae": 0.10074450820684433,
"correlation": 0.30400532484054565,
"activity_accuracy": 0.6242938041687012
},
"osc_2_unison_blend": {
"active_count": 1663,
"mae": 0.052847132086753845,
"correlation": 0.34376639127731323,
"activity_accuracy": 0.6214689016342163
},
"osc_3_on": {
"active_count": 3540,
"mae": 0.48284414410591125,
"correlation": 0.09836041182279587,
"activity_accuracy": 1.0
},
"osc_3_level": {
"active_count": 1832,
"mae": 0.27682730555534363,
"correlation": 0.23588968813419342,
"activity_accuracy": 0.6415254473686218
},
"osc_3_wave_frame": {
"active_count": 1832,
"mae": 0.22454778850078583,
"correlation": 0.10720279812812805,
"activity_accuracy": 0.6451977491378784
},
"osc_3_spectral_morph": {
"active_count": 1832,
"mae": 0.12142474949359894,
"correlation": -0.06585372239351273,
"activity_accuracy": 0.6443502902984619
},
"osc_3_unison_detune": {
"active_count": 971,
"mae": 0.09867705404758453,
"correlation": 0.08085907250642776,
"activity_accuracy": 0.7353107333183289
},
"osc_3_unison_blend": {
"active_count": 971,
"mae": 0.02378300577402115,
"correlation": 0.08953432738780975,
"activity_accuracy": 0.7384181022644043
},
"filter_1_on": {
"active_count": 3540,
"mae": 0.2324187010526657,
"correlation": -0.04407574236392975,
"activity_accuracy": 1.0
},
"filter_1_cutoff": {
"active_count": 2752,
"mae": 0.17478084564208984,
"correlation": 0.07269441336393356,
"activity_accuracy": 0.7867231369018555
},
"filter_1_resonance": {
"active_count": 2752,
"mae": 0.24019108712673187,
"correlation": 0.02128555066883564,
"activity_accuracy": 0.785875678062439
},
"filter_1_drive": {
"active_count": 2752,
"mae": 0.09281659126281738,
"correlation": -0.014594241976737976,
"activity_accuracy": 0.7872881293296814
},
"filter_1_mix": {
"active_count": 2752,
"mae": 0.08064327389001846,
"correlation": -0.04972687363624573,
"activity_accuracy": 0.7870056629180908
},
"filter_2_on": {
"active_count": 3540,
"mae": 0.5053307414054871,
"correlation": 0.12308695912361145,
"activity_accuracy": 1.0
},
"filter_2_cutoff": {
"active_count": 1837,
"mae": 0.1907133311033249,
"correlation": 0.24302536249160767,
"activity_accuracy": 0.6019774079322815
},
"filter_2_resonance": {
"active_count": 1837,
"mae": 0.2358439564704895,
"correlation": -0.03607664257287979,
"activity_accuracy": 0.6050847172737122
},
"filter_2_drive": {
"active_count": 1837,
"mae": 0.09111491590738297,
"correlation": -0.0332634411752224,
"activity_accuracy": 0.6036723256111145
},
"filter_2_mix": {
"active_count": 1837,
"mae": 0.09341227263212204,
"correlation": 0.06699809432029724,
"activity_accuracy": 0.6002824902534485
},
"amp_attack": {
"active_count": 3540,
"mae": 0.041396018117666245,
"correlation": 0.47433802485466003,
"activity_accuracy": 1.0
},
"amp_decay": {
"active_count": 3540,
"mae": 0.03212667256593704,
"correlation": 0.1813156008720398,
"activity_accuracy": 1.0
},
"amp_sustain": {
"active_count": 3540,
"mae": 0.2932977080345154,
"correlation": 0.24054063856601715,
"activity_accuracy": 1.0
},
"amp_release": {
"active_count": 3540,
"mae": 0.04134417697787285,
"correlation": 0.4556550681591034,
"activity_accuracy": 1.0
},
"reverb_on": {
"active_count": 3540,
"mae": 0.2985022962093353,
"correlation": -0.007388888392597437,
"activity_accuracy": 1.0
},
"reverb_dry_wet": {
"active_count": 2514,
"mae": 0.1430150717496872,
"correlation": 0.3627442717552185,
"activity_accuracy": 0.7511299252510071
},
"delay_on": {
"active_count": 3540,
"mae": 0.4575974643230438,
"correlation": 0.30409732460975647,
"activity_accuracy": 1.0
},
"delay_dry_wet": {
"active_count": 1624,
"mae": 0.122687429189682,
"correlation": 0.256661593914032,
"activity_accuracy": 0.5782485604286194
},
"chorus_on": {
"active_count": 3540,
"mae": 0.49554184079170227,
"correlation": 0.03185122460126877,
"activity_accuracy": 1.0
},
"chorus_dry_wet": {
"active_count": 1788,
"mae": 0.1723630279302597,
"correlation": 0.11245910823345184,
"activity_accuracy": 0.598870038986206
},
"distortion_on": {
"active_count": 3540,
"mae": 0.4319402873516083,
"correlation": 0.16361112892627716,
"activity_accuracy": 1.0
},
"distortion_mix": {
"active_count": 2022,
"mae": 0.2764282822608948,
"correlation": 0.2589665651321411,
"activity_accuracy": 0.5790960192680359
}
},
"acoustic_features": {
"rms_level": {
"mae": 0.018084345385432243,
"correlation": 0.9819198250770569
},
"peak_level": {
"mae": 0.1003032997250557,
"correlation": 0.8763360977172852
},
"crest_factor": {
"mae": 0.06021900475025177,
"correlation": 0.9167791604995728
},
"attack_time": {
"mae": 0.04812275990843773,
"correlation": 0.8814619779586792
},
"tail_energy": {
"mae": 0.07377135008573532,
"correlation": 0.9141566753387451
},
"tail_to_body": {
"mae": 0.040361437946558,
"correlation": 0.961588442325592
},
"spectral_centroid": {
"mae": 0.02643768861889839,
"correlation": 0.9523230195045471
},
"spectral_bandwidth": {
"mae": 0.020710788667201996,
"correlation": 0.9231536388397217
},
"spectral_brightness": {
"mae": 0.015201178379356861,
"correlation": 0.9072877764701843
},
"spectral_flatness": {
"mae": 0.02587227337062359,
"correlation": 0.8553925156593323
},
"spectral_flux": {
"mae": 0.024959176778793335,
"correlation": 0.6214450001716614
},
"modulation_depth": {
"mae": 0.0698200911283493,
"correlation": 0.9119333028793335
},
"stereo_width": {
"mae": 0.04248964041471481,
"correlation": 0.9460362792015076
},
"stereo_correlation": {
"mae": 0.04302258789539337,
"correlation": 0.9446200728416443
},
"channel_imbalance": {
"mae": 0.033999886363744736,
"correlation": 0.431243360042572
}
}
}