humaneness-ears-base-medium / evaluation /small /validation_metrics.json
ChristophSchuhmann's picture
Release best Gemini-tuned Whisper Base and Small with code, normalization and evaluation
cd9b2d8 verified
Raw History Blame Contribute Delete
44.8 kB
{
"loss": 1.582846255867744,
"clips": 3239,
"per_score": [
{
"score": "emo_Affection",
"n": 3239,
"raw_mae": 0.3624160885810852,
"normalized_mae": 0.6665286421775818,
"pearson": 0.7804350852966309,
"spearman": 0.6145446436045559
},
{
"score": "emo_Amusement",
"n": 3239,
"raw_mae": 0.4804326593875885,
"normalized_mae": 0.5537136793136597,
"pearson": 0.7681946754455566,
"spearman": 0.6964206664066678
},
{
"score": "emo_Anger",
"n": 3239,
"raw_mae": 0.3147231340408325,
"normalized_mae": 0.5424988865852356,
"pearson": 0.7395689487457275,
"spearman": 0.5373525398319321
},
{
"score": "emo_Astonishment_Surprise",
"n": 3239,
"raw_mae": 0.35966956615448,
"normalized_mae": 0.651341438293457,
"pearson": 0.7330920696258545,
"spearman": 0.6099953603823091
},
{
"score": "emo_Awe",
"n": 3239,
"raw_mae": 0.29291582107543945,
"normalized_mae": 0.6977982521057129,
"pearson": 0.8074489831924438,
"spearman": 0.591786104479248
},
{
"score": "emo_Bitterness",
"n": 3239,
"raw_mae": 0.3405638039112091,
"normalized_mae": 0.8369168043136597,
"pearson": 0.736993134021759,
"spearman": 0.5815680780513529
},
{
"score": "emo_Concentration",
"n": 3239,
"raw_mae": 0.4602629244327545,
"normalized_mae": 0.6299943327903748,
"pearson": 0.7147646546363831,
"spearman": 0.70984525245335
},
{
"score": "emo_Confusion",
"n": 3239,
"raw_mae": 0.3508724570274353,
"normalized_mae": 0.6577999591827393,
"pearson": 0.6716163158416748,
"spearman": 0.5442641292086638
},
{
"score": "emo_Contemplation",
"n": 3239,
"raw_mae": 0.5505203008651733,
"normalized_mae": 0.934756338596344,
"pearson": 0.7532496452331543,
"spearman": 0.7429481766718604
},
{
"score": "emo_Contempt",
"n": 3239,
"raw_mae": 0.3039936423301697,
"normalized_mae": 0.6738394498825073,
"pearson": 0.711904764175415,
"spearman": 0.47521018783767743
},
{
"score": "emo_Contentment",
"n": 3239,
"raw_mae": 0.5345626473426819,
"normalized_mae": 1.0610421895980835,
"pearson": 0.7477469444274902,
"spearman": 0.7388285007230002
},
{
"score": "emo_Disappointment",
"n": 3239,
"raw_mae": 0.42192724347114563,
"normalized_mae": 0.6016004681587219,
"pearson": 0.7657911777496338,
"spearman": 0.6308032608858444
},
{
"score": "emo_Disgust",
"n": 3239,
"raw_mae": 0.21599358320236206,
"normalized_mae": 0.44056054949760437,
"pearson": 0.7217755317687988,
"spearman": 0.4734141864004028
},
{
"score": "emo_Distress",
"n": 3239,
"raw_mae": 0.461065411567688,
"normalized_mae": 0.5640713572502136,
"pearson": 0.7951546907424927,
"spearman": 0.7014823166333529
},
{
"score": "emo_Doubt",
"n": 3239,
"raw_mae": 0.4518052339553833,
"normalized_mae": 0.9347556829452515,
"pearson": 0.6626492738723755,
"spearman": 0.6486423009586768
},
{
"score": "emo_Elation",
"n": 3239,
"raw_mae": 0.32609373331069946,
"normalized_mae": 0.4538790285587311,
"pearson": 0.754449725151062,
"spearman": 0.6073886015390035
},
{
"score": "emo_Embarrassment",
"n": 3239,
"raw_mae": 0.16321206092834473,
"normalized_mae": 0.3734394609928131,
"pearson": 0.6773053407669067,
"spearman": 0.3489144038775482
},
{
"score": "emo_Emotional_Numbness",
"n": 3239,
"raw_mae": 0.24599675834178925,
"normalized_mae": 0.25585585832595825,
"pearson": 0.6076076626777649,
"spearman": 0.4613413190422394
},
{
"score": "emo_Fatigue_Exhaustion",
"n": 3239,
"raw_mae": 0.44413521885871887,
"normalized_mae": 0.8212647438049316,
"pearson": 0.7851437330245972,
"spearman": 0.7150735004273532
},
{
"score": "emo_Fear",
"n": 3239,
"raw_mae": 0.24876557290554047,
"normalized_mae": 0.4066515862941742,
"pearson": 0.6767146587371826,
"spearman": 0.45905839882076055
},
{
"score": "emo_Helplessness",
"n": 3239,
"raw_mae": 0.4143589437007904,
"normalized_mae": 0.5852038860321045,
"pearson": 0.8001692295074463,
"spearman": 0.678428392009325
},
{
"score": "emo_Hope_Enthusiasm_Optimism",
"n": 3239,
"raw_mae": 0.5084466934204102,
"normalized_mae": 0.6703563332557678,
"pearson": 0.7435425519943237,
"spearman": 0.716925364913574
},
{
"score": "emo_Impatience_and_Irritability",
"n": 3239,
"raw_mae": 0.4582568109035492,
"normalized_mae": 0.6698355078697205,
"pearson": 0.7126353979110718,
"spearman": 0.5851355800659597
},
{
"score": "emo_Infatuation",
"n": 3239,
"raw_mae": 0.13445986807346344,
"normalized_mae": 0.24843166768550873,
"pearson": 0.7336952686309814,
"spearman": 0.36283542218562176
},
{
"score": "emo_Interest",
"n": 3239,
"raw_mae": 0.5027316808700562,
"normalized_mae": 0.5499753355979919,
"pearson": 0.7699602842330933,
"spearman": 0.7365851849341749
},
{
"score": "emo_Intoxication_Altered_States_of_Consciousness",
"n": 3239,
"raw_mae": 0.11610563099384308,
"normalized_mae": 0.2087422013282776,
"pearson": 0.5792962312698364,
"spearman": 0.31657831961597427
},
{
"score": "emo_Jealousy_and_Envy",
"n": 3239,
"raw_mae": 0.048485781997442245,
"normalized_mae": 0.10877104848623276,
"pearson": 0.8315446376800537,
"spearman": 0.1407686094210959
},
{
"score": "emo_Longing",
"n": 3239,
"raw_mae": 0.3293037414550781,
"normalized_mae": 0.5179107785224915,
"pearson": 0.7508494853973389,
"spearman": 0.6109489892238265
},
{
"score": "emo_Malevolence_Malice",
"n": 3239,
"raw_mae": 0.16205690801143646,
"normalized_mae": 0.3094550669193268,
"pearson": 0.6200590133666992,
"spearman": 0.3333407542017637
},
{
"score": "emo_Pain",
"n": 3239,
"raw_mae": 0.2743310332298279,
"normalized_mae": 0.4769551157951355,
"pearson": 0.7920997738838196,
"spearman": 0.6038152075880486
},
{
"score": "emo_Pleasure_Ecstasy",
"n": 3239,
"raw_mae": 0.23333099484443665,
"normalized_mae": 0.38217753171920776,
"pearson": 0.7868494987487793,
"spearman": 0.5835895798735868
},
{
"score": "emo_Pride",
"n": 3239,
"raw_mae": 0.4625779092311859,
"normalized_mae": 0.8897233605384827,
"pearson": 0.6956667900085449,
"spearman": 0.5988508331403721
},
{
"score": "emo_Relief",
"n": 3239,
"raw_mae": 0.40225183963775635,
"normalized_mae": 0.576373279094696,
"pearson": 0.7085192203521729,
"spearman": 0.5473095750829268
},
{
"score": "emo_Sadness",
"n": 3239,
"raw_mae": 0.3428352177143097,
"normalized_mae": 0.4485592842102051,
"pearson": 0.795590877532959,
"spearman": 0.5946220425137301
},
{
"score": "emo_Sexual_Lust",
"n": 3239,
"raw_mae": 0.09335370361804962,
"normalized_mae": 0.18755725026130676,
"pearson": 0.6339981555938721,
"spearman": 0.2689131671707554
},
{
"score": "emo_Shame",
"n": 3239,
"raw_mae": 0.09587110579013824,
"normalized_mae": 0.1829526424407959,
"pearson": 0.7804228663444519,
"spearman": 0.28576690767904095
},
{
"score": "emo_Sourness",
"n": 3239,
"raw_mae": 0.3441246747970581,
"normalized_mae": 0.7959120273590088,
"pearson": 0.7327250242233276,
"spearman": 0.559499103904708
},
{
"score": "emo_Teasing",
"n": 3239,
"raw_mae": 0.39198359847068787,
"normalized_mae": 0.7285749912261963,
"pearson": 0.6910577416419983,
"spearman": 0.561652186631223
},
{
"score": "emo_Thankfulness_Gratitude",
"n": 3239,
"raw_mae": 0.20973679423332214,
"normalized_mae": 0.30340006947517395,
"pearson": 0.8089194893836975,
"spearman": 0.5139551311580076
},
{
"score": "emo_Triumph",
"n": 3239,
"raw_mae": 0.3016352653503418,
"normalized_mae": 0.571261465549469,
"pearson": 0.6944113969802856,
"spearman": 0.5115686931830522
},
{
"score": "vn_AGEV_reg",
"n": 3239,
"raw_mae": 0.3151014447212219,
"normalized_mae": 0.2500835657119751,
"pearson": 0.44679027795791626,
"spearman": 0.43355406272917707
},
{
"score": "vn_AROU_reg",
"n": 3239,
"raw_mae": 0.5240619778633118,
"normalized_mae": 0.46520039439201355,
"pearson": 0.7515125870704651,
"spearman": 0.7253643536833201
},
{
"score": "vn_ARSH_reg",
"n": 3239,
"raw_mae": 0.4749733507633209,
"normalized_mae": 0.5420278310775757,
"pearson": 0.3830987215042114,
"spearman": 0.34840587495222297
},
{
"score": "vn_ATCK_reg",
"n": 3239,
"raw_mae": 0.46310681104660034,
"normalized_mae": 0.3517081141471863,
"pearson": 0.7055434584617615,
"spearman": 0.6885166576898267
},
{
"score": "vn_BKGN_reg",
"n": 3239,
"raw_mae": 0.33509206771850586,
"normalized_mae": 0.4428357481956482,
"pearson": 0.6122440695762634,
"spearman": 0.6176309016127476
},
{
"score": "vn_BRGT_reg",
"n": 3239,
"raw_mae": 0.3770935535430908,
"normalized_mae": 0.46519938111305237,
"pearson": 0.683281660079956,
"spearman": 0.6666298152516151
},
{
"score": "vn_CHNK_reg",
"n": 3239,
"raw_mae": 0.4083485007286072,
"normalized_mae": 0.3275942802429199,
"pearson": 0.7365280389785767,
"spearman": 0.7376497383218785
},
{
"score": "vn_CLRT_reg",
"n": 3239,
"raw_mae": 0.4402329921722412,
"normalized_mae": 0.4581398069858551,
"pearson": 0.7978527545928955,
"spearman": 0.7143117987648939
},
{
"score": "vn_COGL_reg",
"n": 3239,
"raw_mae": 0.5510599613189697,
"normalized_mae": 0.5227269530296326,
"pearson": 0.7569067478179932,
"spearman": 0.7641185743622113
},
{
"score": "vn_DARC_reg",
"n": 3239,
"raw_mae": 0.4614301025867462,
"normalized_mae": 0.3387516438961029,
"pearson": 0.42335909605026245,
"spearman": 0.39184040015223387
},
{
"score": "vn_DFLU_reg",
"n": 3239,
"raw_mae": 0.5876264572143555,
"normalized_mae": 0.49749818444252014,
"pearson": 0.7993061542510986,
"spearman": 0.8013994578017339
},
{
"score": "vn_EMPH_reg",
"n": 3239,
"raw_mae": 0.44825419783592224,
"normalized_mae": 0.2852988541126251,
"pearson": 0.6698497533798218,
"spearman": 0.6340550582213186
},
{
"score": "vn_ESTH_reg",
"n": 3239,
"raw_mae": 0.45043399930000305,
"normalized_mae": 0.5784369707107544,
"pearson": 0.7387670278549194,
"spearman": 0.7071414759013891
},
{
"score": "vn_EXPL_reg",
"n": 3239,
"raw_mae": 0.10685891658067703,
"normalized_mae": 0.3263363540172577,
"pearson": 0.29849332571029663,
"spearman": 0.19301436866232488
},
{
"score": "vn_FOCS_reg",
"n": 3239,
"raw_mae": 0.414010226726532,
"normalized_mae": 0.3730304539203644,
"pearson": 0.6488807201385498,
"spearman": 0.5305457197514858
},
{
"score": "vn_FULL_reg",
"n": 3239,
"raw_mae": 0.35945504903793335,
"normalized_mae": 0.4067741632461548,
"pearson": 0.5769761800765991,
"spearman": 0.5736490878262412
},
{
"score": "vn_GEND_reg",
"n": 3239,
"raw_mae": 0.5887286067008972,
"normalized_mae": 0.3696889281272888,
"pearson": 0.8689672350883484,
"spearman": 0.7957844578148172
},
{
"score": "vn_HARM_reg",
"n": 3239,
"raw_mae": 0.47598543763160706,
"normalized_mae": 0.5749129056930542,
"pearson": 0.7045425176620483,
"spearman": 0.6768769177771036
},
{
"score": "vn_METL_reg",
"n": 3239,
"raw_mae": 0.47653183341026306,
"normalized_mae": 0.4976053237915039,
"pearson": 0.6435381174087524,
"spearman": 0.5941200562277026
},
{
"score": "vn_RANG_reg",
"n": 3239,
"raw_mae": 0.5032981038093567,
"normalized_mae": 0.5645459890365601,
"pearson": 0.7490918040275574,
"spearman": 0.75039249276355
},
{
"score": "vn_RCQL_reg",
"n": 3239,
"raw_mae": 0.41259175539016724,
"normalized_mae": 0.4583285450935364,
"pearson": 0.6261029243469238,
"spearman": 0.6455342520224854
},
{
"score": "vn_REGS_reg",
"n": 3239,
"raw_mae": 0.48673614859580994,
"normalized_mae": 0.38747069239616394,
"pearson": 0.8547676801681519,
"spearman": 0.8106873827987178
},
{
"score": "vn_RESP_reg",
"n": 3239,
"raw_mae": 0.4338551163673401,
"normalized_mae": 0.4056472182273865,
"pearson": 0.8404936790466309,
"spearman": 0.7974656489453886
},
{
"score": "vn_ROUG_reg",
"n": 3239,
"raw_mae": 0.5115371942520142,
"normalized_mae": 0.5801653861999512,
"pearson": 0.7723860740661621,
"spearman": 0.7317493569024084
},
{
"score": "vn_R_CHST_reg",
"n": 3239,
"raw_mae": 0.4732091426849365,
"normalized_mae": 0.5573493242263794,
"pearson": 0.7607860565185547,
"spearman": 0.7588288337040379
},
{
"score": "vn_R_HEAD_reg",
"n": 3239,
"raw_mae": 0.511212944984436,
"normalized_mae": 0.6207306385040283,
"pearson": 0.7646077871322632,
"spearman": 0.7597287289074481
},
{
"score": "vn_R_MASK_reg",
"n": 3239,
"raw_mae": 0.43624788522720337,
"normalized_mae": 0.42627450823783875,
"pearson": 0.7051059007644653,
"spearman": 0.6808067288560888
},
{
"score": "vn_R_MIXD_reg",
"n": 3239,
"raw_mae": 0.40111464262008667,
"normalized_mae": 0.47930774092674255,
"pearson": 0.6443465352058411,
"spearman": 0.6042192490335143
},
{
"score": "vn_R_NASL_reg",
"n": 3239,
"raw_mae": 0.39269137382507324,
"normalized_mae": 0.3718317449092865,
"pearson": 0.516772985458374,
"spearman": 0.5081353032317345
},
{
"score": "vn_R_ORAL_reg",
"n": 3239,
"raw_mae": 0.35402241349220276,
"normalized_mae": 0.47577613592147827,
"pearson": 0.6250635385513306,
"spearman": 0.6192921914855405
},
{
"score": "vn_R_THRT_reg",
"n": 3239,
"raw_mae": 0.4258991479873657,
"normalized_mae": 0.5288863182067871,
"pearson": 0.7228474617004395,
"spearman": 0.6922009616688952
},
{
"score": "vn_SMTH_reg",
"n": 3239,
"raw_mae": 0.4619424045085907,
"normalized_mae": 0.41565069556236267,
"pearson": 0.738714337348938,
"spearman": 0.7418142060616335
},
{
"score": "vn_STNC_reg",
"n": 3239,
"raw_mae": 0.6057895421981812,
"normalized_mae": 0.5320228338241577,
"pearson": 0.7080386877059937,
"spearman": 0.6793874497616369
},
{
"score": "vn_STRU_reg",
"n": 3239,
"raw_mae": 0.47764769196510315,
"normalized_mae": 0.4843936264514923,
"pearson": 0.7858661413192749,
"spearman": 0.7526642592900243
},
{
"score": "vn_S_ASMR_reg",
"n": 3239,
"raw_mae": 0.561885416507721,
"normalized_mae": 0.40754225850105286,
"pearson": 0.7416295409202576,
"spearman": 0.6989639508807581
},
{
"score": "vn_S_AUTH_reg",
"n": 3239,
"raw_mae": 0.6564152240753174,
"normalized_mae": 0.6318506598472595,
"pearson": 0.7603013515472412,
"spearman": 0.7510351273420746
},
{
"score": "vn_S_CART_reg",
"n": 3239,
"raw_mae": 0.601181149482727,
"normalized_mae": 0.4390769898891449,
"pearson": 0.6562930941581726,
"spearman": 0.6036560290743876
},
{
"score": "vn_S_CASU_reg",
"n": 3239,
"raw_mae": 0.7437771558761597,
"normalized_mae": 0.5829437971115112,
"pearson": 0.7586772441864014,
"spearman": 0.7726225037699617
},
{
"score": "vn_S_CONV_reg",
"n": 3239,
"raw_mae": 0.6736096739768982,
"normalized_mae": 0.5160374045372009,
"pearson": 0.7842527031898499,
"spearman": 0.7755242191211487
},
{
"score": "vn_S_DRAM_reg",
"n": 3239,
"raw_mae": 0.6699936389923096,
"normalized_mae": 0.588067889213562,
"pearson": 0.8106591701507568,
"spearman": 0.81371758822181
},
{
"score": "vn_S_FORM_reg",
"n": 3239,
"raw_mae": 0.6104399561882019,
"normalized_mae": 0.6053935289382935,
"pearson": 0.7729653120040894,
"spearman": 0.7714929135870394
},
{
"score": "vn_S_MONO_reg",
"n": 3239,
"raw_mae": 0.8231870532035828,
"normalized_mae": 0.6470005512237549,
"pearson": 0.6918551325798035,
"spearman": 0.6891663951369431
},
{
"score": "vn_S_NARR_reg",
"n": 3239,
"raw_mae": 0.6765583753585815,
"normalized_mae": 0.47139158844947815,
"pearson": 0.799296498298645,
"spearman": 0.792600007982173
},
{
"score": "vn_S_NEWS_reg",
"n": 3239,
"raw_mae": 0.46908512711524963,
"normalized_mae": 0.8513267040252686,
"pearson": 0.7333018779754639,
"spearman": 0.6996003961139323
},
{
"score": "vn_S_PLAY_reg",
"n": 3239,
"raw_mae": 0.7652629017829895,
"normalized_mae": 0.5886642932891846,
"pearson": 0.721048891544342,
"spearman": 0.7111497791750536
},
{
"score": "vn_S_RANT_reg",
"n": 3239,
"raw_mae": 0.5985997915267944,
"normalized_mae": 0.4691445827484131,
"pearson": 0.703834056854248,
"spearman": 0.5940226209570071
},
{
"score": "vn_S_STRY_reg",
"n": 3239,
"raw_mae": 0.7321662902832031,
"normalized_mae": 0.5253567099571228,
"pearson": 0.6788910031318665,
"spearman": 0.6774313468942407
},
{
"score": "vn_S_TECH_reg",
"n": 3239,
"raw_mae": 0.6574852466583252,
"normalized_mae": 0.5398364067077637,
"pearson": 0.7670819163322449,
"spearman": 0.7935377172978068
},
{
"score": "vn_S_WHIS_reg",
"n": 3239,
"raw_mae": 0.5303695797920227,
"normalized_mae": 0.3317584693431854,
"pearson": 0.7083675861358643,
"spearman": 0.6811211796320856
},
{
"score": "vn_TEMP_reg",
"n": 3239,
"raw_mae": 0.4138309359550476,
"normalized_mae": 0.3446694016456604,
"pearson": 0.7658510804176331,
"spearman": 0.7501708151648724
},
{
"score": "vn_TENS_reg",
"n": 3239,
"raw_mae": 0.48357006907463074,
"normalized_mae": 0.5810190439224243,
"pearson": 0.7432616949081421,
"spearman": 0.647006827832255
},
{
"score": "vn_VALN_reg",
"n": 3239,
"raw_mae": 0.6338969469070435,
"normalized_mae": 0.5610315203666687,
"pearson": 0.7645250558853149,
"spearman": 0.7473117268741137
},
{
"score": "vn_VALS_reg",
"n": 3239,
"raw_mae": 0.40787702798843384,
"normalized_mae": 0.37137192487716675,
"pearson": 0.5371129512786865,
"spearman": 0.4994206597592
},
{
"score": "vn_VFLX_reg",
"n": 3239,
"raw_mae": 0.3189198076725006,
"normalized_mae": 0.26427528262138367,
"pearson": 0.22337235510349274,
"spearman": 0.2191556882969858
},
{
"score": "vn_VOLT_reg",
"n": 3239,
"raw_mae": 0.44773611426353455,
"normalized_mae": 0.5155537128448486,
"pearson": 0.7385282516479492,
"spearman": 0.7220094279113786
},
{
"score": "vn_VULN_reg",
"n": 3239,
"raw_mae": 0.6501423716545105,
"normalized_mae": 0.6563625931739807,
"pearson": 0.7780672311782837,
"spearman": 0.7476541615729596
},
{
"score": "vn_WARM_reg",
"n": 3239,
"raw_mae": 0.44257739186286926,
"normalized_mae": 0.48911428451538086,
"pearson": 0.6585670113563538,
"spearman": 0.6254561475067277
},
{
"score": "genuineness_0_6",
"n": 3239,
"raw_mae": 0.47298434376716614,
"normalized_mae": 0.29438868165016174,
"pearson": 0.5612930655479431,
"spearman": 0.5956699996898118
},
{
"score": "blend_0_10",
"n": 2192,
"raw_mae": 0.836739718914032,
"normalized_mae": 0.3078543543815613,
"pearson": 0.2855517268180847,
"spearman": 0.30337797584649956
},
{
"score": "R_quality",
"n": 2129,
"raw_mae": 0.09865064173936844,
"normalized_mae": 0.2979392111301422,
"pearson": 0.9333481788635254,
"spearman": 0.9170821410633745
},
{
"score": "eiv_extra:Age",
"n": 3089,
"raw_mae": 0.1251470446586609,
"normalized_mae": 0.42422041296958923,
"pearson": 0.8654205799102783,
"spearman": 0.734125131577543
},
{
"score": "eiv_extra:Arousal",
"n": 3089,
"raw_mae": 0.24195173382759094,
"normalized_mae": 0.5549588799476624,
"pearson": 0.8819342851638794,
"spearman": 0.8932880035816936
},
{
"score": "eiv_extra:Authenticity",
"n": 3089,
"raw_mae": 0.08878675848245621,
"normalized_mae": 0.35514703392982483,
"pearson": 0.9235581159591675,
"spearman": 0.9250719998597563
},
{
"score": "eiv_extra:Background_Noise",
"n": 3089,
"raw_mae": 0.1271778643131256,
"normalized_mae": 0.4818326532840729,
"pearson": 0.902705192565918,
"spearman": 0.8765099897096076
},
{
"score": "eiv_extra:Confident_vs._Hesitant",
"n": 3089,
"raw_mae": 0.15440529584884644,
"normalized_mae": 0.5077310800552368,
"pearson": 0.926205039024353,
"spearman": 0.9301959952063759
},
{
"score": "eiv_extra:Gender",
"n": 3089,
"raw_mae": 0.2466585338115692,
"normalized_mae": 0.24730663001537323,
"pearson": 0.9477115273475647,
"spearman": 0.9293151914148688
},
{
"score": "eiv_extra:High-Pitched_vs._Low-Pitched",
"n": 3089,
"raw_mae": 0.0796910747885704,
"normalized_mae": 0.3187642991542816,
"pearson": 0.9527561068534851,
"spearman": 0.9542424909453803
},
{
"score": "eiv_extra:Monotone_vs._Expressive",
"n": 3089,
"raw_mae": 0.14755821228027344,
"normalized_mae": 0.3137950897216797,
"pearson": 0.9457440376281738,
"spearman": 0.9460897828085162
},
{
"score": "eiv_extra:Recording_Quality",
"n": 3089,
"raw_mae": 0.125826895236969,
"normalized_mae": 0.37833720445632935,
"pearson": 0.9565455913543701,
"spearman": 0.9575794083614267
},
{
"score": "eiv_extra:Serious_vs._Humorous",
"n": 3089,
"raw_mae": 0.18248406052589417,
"normalized_mae": 0.5352832674980164,
"pearson": 0.8844753503799438,
"spearman": 0.8587305369643139
},
{
"score": "eiv_extra:Soft_vs._Harsh",
"n": 3089,
"raw_mae": 0.1647123545408249,
"normalized_mae": 0.5156802535057068,
"pearson": 0.8278334140777588,
"spearman": 0.8293019217827197
},
{
"score": "eiv_extra:Submissive_vs._Dominant",
"n": 3089,
"raw_mae": 0.13820917904376984,
"normalized_mae": 0.42769667506217957,
"pearson": 0.864608645439148,
"spearman": 0.8586204666068122
},
{
"score": "eiv_extra:Valence",
"n": 3089,
"raw_mae": 0.3294723331928253,
"normalized_mae": 0.8633326292037964,
"pearson": 0.8931715488433838,
"spearman": 0.841211323168285
},
{
"score": "eiv_extra:Vulnerable_vs._Emotionally_Detached",
"n": 3089,
"raw_mae": 0.1544128954410553,
"normalized_mae": 0.35431593656539917,
"pearson": 0.9325900077819824,
"spearman": 0.9292586330978918
},
{
"score": "eiv_extra:Warm_vs._Cold",
"n": 3089,
"raw_mae": 0.1776563674211502,
"normalized_mae": 0.5923417210578918,
"pearson": 0.8454700708389282,
"spearman": 0.8211886539479363
},
{
"score": "eiv_extra:score_background_quality",
"n": 3089,
"raw_mae": 0.10122620314359665,
"normalized_mae": 0.14594464004039764,
"pearson": 0.9520081281661987,
"spearman": 0.9040267572683414
},
{
"score": "eiv_extra:score_content_enjoyment",
"n": 3089,
"raw_mae": 0.07215617597103119,
"normalized_mae": 0.2375376671552658,
"pearson": 0.9593187570571899,
"spearman": 0.9515489417751302
},
{
"score": "eiv_extra:score_overall_quality",
"n": 3089,
"raw_mae": 0.08071909099817276,
"normalized_mae": 0.1590399444103241,
"pearson": 0.9631538391113281,
"spearman": 0.9431940943193192
},
{
"score": "eiv_extra:score_speech_quality",
"n": 3089,
"raw_mae": 0.044564589858055115,
"normalized_mae": 0.17825835943222046,
"pearson": 0.8595994114875793,
"spearman": 0.7836760855463243
},
{
"score": "audiobox:CE",
"n": 3239,
"raw_mae": 0.18344847857952118,
"normalized_mae": 0.1804419755935669,
"pearson": 0.9579653739929199,
"spearman": 0.9526983969735731
},
{
"score": "audiobox:CU",
"n": 3239,
"raw_mae": 0.19470709562301636,
"normalized_mae": 0.19492454826831818,
"pearson": 0.9506620168685913,
"spearman": 0.9517388137900714
},
{
"score": "audiobox:PC",
"n": 3239,
"raw_mae": 0.1192006915807724,
"normalized_mae": 0.07378622144460678,
"pearson": 0.9617234468460083,
"spearman": 0.8235071771615938
},
{
"score": "audiobox:PQ",
"n": 3239,
"raw_mae": 0.19561272859573364,
"normalized_mae": 0.22247213125228882,
"pearson": 0.9516366720199585,
"spearman": 0.9461204299153108
},
{
"score": "dnsmos:SIG_raw",
"n": 3089,
"raw_mae": 0.1454436480998993,
"normalized_mae": 0.2173812985420227,
"pearson": 0.9042521119117737,
"spearman": 0.8667307874568158
},
{
"score": "dnsmos:BAK_raw",
"n": 3089,
"raw_mae": 0.2045021951198578,
"normalized_mae": 0.18174001574516296,
"pearson": 0.9280752539634705,
"spearman": 0.8884071782289495
},
{
"score": "dnsmos:OVRL_raw",
"n": 3089,
"raw_mae": 0.17178086936473846,
"normalized_mae": 0.2112952172756195,
"pearson": 0.9331422448158264,
"spearman": 0.9076432260648124
},
{
"score": "dnsmos:SIG",
"n": 3089,
"raw_mae": 0.09186159819364548,
"normalized_mae": 0.18330518901348114,
"pearson": 0.8992406129837036,
"spearman": 0.863955544886444
},
{
"score": "dnsmos:BAK",
"n": 3089,
"raw_mae": 0.14099815487861633,
"normalized_mae": 0.15184488892555237,
"pearson": 0.929247260093689,
"spearman": 0.8774887802496547
},
{
"score": "dnsmos:OVRL",
"n": 3089,
"raw_mae": 0.1153024360537529,
"normalized_mae": 0.1900627613067627,
"pearson": 0.9342350363731384,
"spearman": 0.9075465830345022
},
{
"score": "dnsmos:P808_MOS",
"n": 3089,
"raw_mae": 0.1174275204539299,
"normalized_mae": 0.23654673993587494,
"pearson": 0.928391695022583,
"spearman": 0.8811174960446772
},
{
"score": "burst_count_log1p",
"n": 3239,
"raw_mae": 0.2515793740749359,
"normalized_mae": 0.3879280686378479,
"pearson": 0.8359383344650269,
"spearman": 0.8248559024783457
},
{
"score": "voiceclap_attribute:Affection",
"n": 3239,
"raw_mae": 0.46478867530822754,
"normalized_mae": 0.8382025957107544,
"pearson": 0.6894074082374573,
"spearman": 0.5561567139294018
},
{
"score": "voiceclap_attribute:Age",
"n": 3089,
"raw_mae": 0.14456522464752197,
"normalized_mae": 0.26586663722991943,
"pearson": 0.8336584568023682,
"spearman": 0.7502140020846737
},
{
"score": "voiceclap_attribute:Amusement",
"n": 3239,
"raw_mae": 0.5394867062568665,
"normalized_mae": 0.9400410652160645,
"pearson": 0.7399063110351562,
"spearman": 0.6687812863526655
},
{
"score": "voiceclap_attribute:Anger",
"n": 3239,
"raw_mae": 0.37503132224082947,
"normalized_mae": 0.7391657829284668,
"pearson": 0.6705925464630127,
"spearman": 0.5110208995311883
},
{
"score": "voiceclap_attribute:Arousal",
"n": 3089,
"raw_mae": 0.2911946177482605,
"normalized_mae": 0.467708557844162,
"pearson": 0.8338792324066162,
"spearman": 0.845400339439839
},
{
"score": "voiceclap_attribute:Astonishment_Surprise",
"n": 3239,
"raw_mae": 0.4636822044849396,
"normalized_mae": 0.9682837128639221,
"pearson": 0.6425167322158813,
"spearman": 0.5503884106244362
},
{
"score": "voiceclap_attribute:Authenticity",
"n": 3089,
"raw_mae": 0.09301295131444931,
"normalized_mae": 0.37205180525779724,
"pearson": 0.8827534317970276,
"spearman": 0.8901055703270261
},
{
"score": "voiceclap_attribute:Awe",
"n": 3239,
"raw_mae": 0.39997726678848267,
"normalized_mae": 1.5418707132339478,
"pearson": 0.7386765480041504,
"spearman": 0.5532543865295745
},
{
"score": "voiceclap_attribute:Background_Noise",
"n": 3089,
"raw_mae": 0.09909151494503021,
"normalized_mae": 0.3752039968967438,
"pearson": 0.87943035364151,
"spearman": 0.8755293392225584
},
{
"score": "voiceclap_attribute:Bitterness",
"n": 3239,
"raw_mae": 0.41125428676605225,
"normalized_mae": 1.645017147064209,
"pearson": 0.6989700198173523,
"spearman": 0.5524874916572137
},
{
"score": "voiceclap_attribute:Concentration",
"n": 3239,
"raw_mae": 0.49213266372680664,
"normalized_mae": 0.9276638031005859,
"pearson": 0.663593053817749,
"spearman": 0.6563300898784001
},
{
"score": "voiceclap_attribute:Confident_vs._Hesitant",
"n": 3089,
"raw_mae": 0.22347140312194824,
"normalized_mae": 0.47670215368270874,
"pearson": 0.8506917953491211,
"spearman": 0.8543624926928821
},
{
"score": "voiceclap_attribute:Confusion",
"n": 3239,
"raw_mae": 0.4418790340423584,
"normalized_mae": 1.3182053565979004,
"pearson": 0.5294662714004517,
"spearman": 0.48449122104571335
},
{
"score": "voiceclap_attribute:Contemplation",
"n": 3239,
"raw_mae": 0.6288188695907593,
"normalized_mae": 1.551324725151062,
"pearson": 0.6768484115600586,
"spearman": 0.6578474449744881
},
{
"score": "voiceclap_attribute:Contempt",
"n": 3239,
"raw_mae": 0.37687164545059204,
"normalized_mae": 1.1094462871551514,
"pearson": 0.6488301753997803,
"spearman": 0.4329452355396376
},
{
"score": "voiceclap_attribute:Contentment",
"n": 3239,
"raw_mae": 0.6058357357978821,
"normalized_mae": 1.9736979007720947,
"pearson": 0.7061485648155212,
"spearman": 0.7054222790283609
},
{
"score": "voiceclap_attribute:Disappointment",
"n": 3239,
"raw_mae": 0.477384090423584,
"normalized_mae": 1.6431456804275513,
"pearson": 0.713414192199707,
"spearman": 0.5910324787017764
},
{
"score": "voiceclap_attribute:Disgust",
"n": 3239,
"raw_mae": 0.2689250409603119,
"normalized_mae": 1.0757001638412476,
"pearson": 0.630492091178894,
"spearman": 0.4444717500193869
},
{
"score": "voiceclap_attribute:Distress",
"n": 3239,
"raw_mae": 0.4971165657043457,
"normalized_mae": 1.4204598665237427,
"pearson": 0.7724372148513794,
"spearman": 0.6828616131909504
},
{
"score": "voiceclap_attribute:Doubt",
"n": 3239,
"raw_mae": 0.5172457695007324,
"normalized_mae": 2.0689830780029297,
"pearson": 0.5740839242935181,
"spearman": 0.5905869829091359
},
{
"score": "voiceclap_attribute:Elation",
"n": 3239,
"raw_mae": 0.40108034014701843,
"normalized_mae": 1.0058763027191162,
"pearson": 0.6968157291412354,
"spearman": 0.5797083014158103
},
{
"score": "voiceclap_attribute:Embarrassment",
"n": 3239,
"raw_mae": 0.2081916779279709,
"normalized_mae": 0.6615263223648071,
"pearson": 0.3351164758205414,
"spearman": 0.2820356270639637
},
{
"score": "voiceclap_attribute:Emotional_Numbness",
"n": 3239,
"raw_mae": 0.26927751302719116,
"normalized_mae": 1.0116416215896606,
"pearson": 0.30719780921936035,
"spearman": 0.302588247982403
},
{
"score": "voiceclap_attribute:Fatigue_Exhaustion",
"n": 3239,
"raw_mae": 0.49428999423980713,
"normalized_mae": 1.8988170623779297,
"pearson": 0.7499858140945435,
"spearman": 0.7036973629794138
},
{
"score": "voiceclap_attribute:Fear",
"n": 3239,
"raw_mae": 0.3143538236618042,
"normalized_mae": 1.2574152946472168,
"pearson": 0.5401285886764526,
"spearman": 0.42984725210261926
},
{
"score": "voiceclap_attribute:Gender",
"n": 3089,
"raw_mae": 0.23999176919460297,
"normalized_mae": 0.23889100551605225,
"pearson": 0.9439729452133179,
"spearman": 0.9262493376331604
},
{
"score": "voiceclap_attribute:Helplessness",
"n": 3239,
"raw_mae": 0.472966730594635,
"normalized_mae": 1.7630261182785034,
"pearson": 0.7708054184913635,
"spearman": 0.6587378389427455
},
{
"score": "voiceclap_attribute:High-Pitched_vs._Low-Pitched",
"n": 3089,
"raw_mae": 0.1333554983139038,
"normalized_mae": 0.35701310634613037,
"pearson": 0.8582569360733032,
"spearman": 0.8639262984160951
},
{
"score": "voiceclap_attribute:Hope_Enthusiasm_Optimism",
"n": 3239,
"raw_mae": 0.5467579960823059,
"normalized_mae": 1.3761929273605347,
"pearson": 0.7031643390655518,
"spearman": 0.6879286914327764
},
{
"score": "voiceclap_attribute:Impatience_and_Irritability",
"n": 3239,
"raw_mae": 0.5216100215911865,
"normalized_mae": 0.9623274803161621,
"pearson": 0.6570683717727661,
"spearman": 0.550644242587609
},
{
"score": "voiceclap_attribute:Infatuation",
"n": 3239,
"raw_mae": 0.20026084780693054,
"normalized_mae": 0.6020975708961487,
"pearson": 0.4430803060531616,
"spearman": 0.33083532080592326
},
{
"score": "voiceclap_attribute:Interest",
"n": 3239,
"raw_mae": 0.5443493127822876,
"normalized_mae": 1.2390320301055908,
"pearson": 0.731494128704071,
"spearman": 0.6954089475177675
},
{
"score": "voiceclap_attribute:Intoxication_Altered_States_of_Consciousness",
"n": 3239,
"raw_mae": 0.17385229468345642,
"normalized_mae": 0.3747062385082245,
"pearson": 0.28136715292930603,
"spearman": 0.24305004878963968
},
{
"score": "voiceclap_attribute:Jealousy_&_Envy",
"n": 3239,
"raw_mae": 0.0956801250576973,
"normalized_mae": 0.3827205002307892,
"pearson": 0.18253259360790253,
"spearman": 0.1098512471400321
},
{
"score": "voiceclap_attribute:Longing",
"n": 3239,
"raw_mae": 0.41696521639823914,
"normalized_mae": 1.6678608655929565,
"pearson": 0.6127288341522217,
"spearman": 0.5773020052368131
},
{
"score": "voiceclap_attribute:Malevolence_Malice",
"n": 3239,
"raw_mae": 0.2193121612071991,
"normalized_mae": 0.6338505744934082,
"pearson": 0.42709386348724365,
"spearman": 0.3278388302288823
},
{
"score": "voiceclap_attribute:Monotone_vs._Expressive",
"n": 3089,
"raw_mae": 0.23093090951442719,
"normalized_mae": 0.38716694712638855,
"pearson": 0.8715511560440063,
"spearman": 0.855919559924785
},
{
"score": "voiceclap_attribute:Pain",
"n": 3239,
"raw_mae": 0.36464041471481323,
"normalized_mae": 1.458561658859253,
"pearson": 0.7116669416427612,
"spearman": 0.6012336477309095
},
{
"score": "voiceclap_attribute:Pleasure_Ecstasy",
"n": 3239,
"raw_mae": 0.3071141541004181,
"normalized_mae": 1.0196293592453003,
"pearson": 0.7020449042320251,
"spearman": 0.5501698607996587
},
{
"score": "voiceclap_attribute:Pride",
"n": 3239,
"raw_mae": 0.5249341726303101,
"normalized_mae": 1.5041558742523193,
"pearson": 0.5849856734275818,
"spearman": 0.5516390405080989
},
{
"score": "voiceclap_attribute:Recording_Quality",
"n": 3089,
"raw_mae": 0.13308334350585938,
"normalized_mae": 0.40559276938438416,
"pearson": 0.9181739091873169,
"spearman": 0.9220500837276273
},
{
"score": "voiceclap_attribute:Relief",
"n": 3239,
"raw_mae": 0.4681965410709381,
"normalized_mae": 1.1256104707717896,
"pearson": 0.6132972240447998,
"spearman": 0.49148643273294096
},
{
"score": "voiceclap_attribute:Sadness",
"n": 3239,
"raw_mae": 0.4101768434047699,
"normalized_mae": 1.3108034133911133,
"pearson": 0.7305837273597717,
"spearman": 0.5737776704156328
},
{
"score": "voiceclap_attribute:Serious_vs._Humorous",
"n": 3089,
"raw_mae": 0.20096427202224731,
"normalized_mae": 0.35228022933006287,
"pearson": 0.8941868543624878,
"spearman": 0.842607969207186
},
{
"score": "voiceclap_attribute:Sexual_Lust",
"n": 3239,
"raw_mae": 0.14467570185661316,
"normalized_mae": 0.3462357223033905,
"pearson": 0.2325618714094162,
"spearman": 0.21193567263056043
},
{
"score": "voiceclap_attribute:Shame",
"n": 3239,
"raw_mae": 0.16184256970882416,
"normalized_mae": 0.5743461847305298,
"pearson": 0.3697497248649597,
"spearman": 0.22042696913033763
},
{
"score": "voiceclap_attribute:Soft_vs._Harsh",
"n": 3089,
"raw_mae": 0.17582917213439941,
"normalized_mae": 0.4881965219974518,
"pearson": 0.804598331451416,
"spearman": 0.8155528043306858
},
{
"score": "voiceclap_attribute:Sourness",
"n": 3239,
"raw_mae": 0.40499475598335266,
"normalized_mae": 1.3941899538040161,
"pearson": 0.6850731372833252,
"spearman": 0.539446524798312
},
{
"score": "voiceclap_attribute:Submissive_vs._Dominant",
"n": 3089,
"raw_mae": 0.15733033418655396,
"normalized_mae": 0.4382413625717163,
"pearson": 0.8177239894866943,
"spearman": 0.824456502820837
},
{
"score": "voiceclap_attribute:Teasing",
"n": 3239,
"raw_mae": 0.46219417452812195,
"normalized_mae": 1.218393325805664,
"pearson": 0.6424816250801086,
"spearman": 0.5301045499471515
},
{
"score": "voiceclap_attribute:Thankfulness_Gratitude",
"n": 3239,
"raw_mae": 0.3275446891784668,
"normalized_mae": 0.618764340877533,
"pearson": 0.6300103068351746,
"spearman": 0.46709305433851556
},
{
"score": "voiceclap_attribute:Triumph",
"n": 3239,
"raw_mae": 0.3787020742893219,
"normalized_mae": 1.0555524826049805,
"pearson": 0.5524948239326477,
"spearman": 0.45191363863536677
},
{
"score": "voiceclap_attribute:Valence",
"n": 3089,
"raw_mae": 0.4397704601287842,
"normalized_mae": 0.6935648918151855,
"pearson": 0.7448421716690063,
"spearman": 0.7397650305086985
},
{
"score": "voiceclap_attribute:Vulnerable_vs._Emotionally_Detached",
"n": 3089,
"raw_mae": 0.21403814852237701,
"normalized_mae": 0.3850415349006653,
"pearson": 0.8624390363693237,
"spearman": 0.8590273016528198
},
{
"score": "voiceclap_attribute:Warm_vs._Cold",
"n": 3089,
"raw_mae": 0.23356081545352936,
"normalized_mae": 0.5848369002342224,
"pearson": 0.7868248224258423,
"spearman": 0.7798371695797178
},
{
"score": "voiceclap_attribute:duration",
"n": 3089,
"raw_mae": 1.081497311592102,
"normalized_mae": 0.17075413465499878,
"pearson": 0.9660919904708862,
"spearman": 0.9625690227657832
},
{
"score": "voiceclap_attribute:score_background_quality",
"n": 3089,
"raw_mae": 0.1223151683807373,
"normalized_mae": 0.24534083902835846,
"pearson": 0.8781657814979553,
"spearman": 0.8605112353357108
},
{
"score": "voiceclap_attribute:score_content_enjoyment",
"n": 3089,
"raw_mae": 0.06368657201528549,
"normalized_mae": 0.25474628806114197,
"pearson": 0.8983961939811707,
"spearman": 0.913831884825405
},
{
"score": "voiceclap_attribute:score_overall_quality",
"n": 3089,
"raw_mae": 0.09499726444482803,
"normalized_mae": 0.23040670156478882,
"pearson": 0.919763445854187,
"spearman": 0.9098135943945252
},
{
"score": "voiceclap_attribute:score_speech_quality",
"n": 3089,
"raw_mae": 0.026841286569833755,
"normalized_mae": 0.10736514627933502,
"pearson": 0.8559004068374634,
"spearman": 0.8459151873894386
},
{
"score": "voiceclap_attribute:talking_speed",
"n": 3089,
"raw_mae": 1.3529478311538696,
"normalized_mae": 0.3605680465698242,
"pearson": 0.9281216859817505,
"spearman": 0.9272271176987172
}
],
"speaker_cosine": {
"timbre": {
"n": 1447,
"mean": 0.931404589762256
},
"identity": {
"n": 1447,
"mean": 0.8876386035823295
}
},
"frame_f1": 0.7044607859017137,
"frame_threshold": 0.5,
"cps_raw_mae": 0.9162952663231166,
"burst_class_oracle_span_accuracy": 0.4583781458378146,
"burst_class_events": 4649,
"burst_localization": {
"0.1": {
"precision": 0.12810293425388358,
"recall": 0.8780382878038288,
"f1": 0.2235854740647423,
"matched": 4082
},
"0.3": {
"precision": 0.12336419268790208,
"recall": 0.8455581845558184,
"f1": 0.21531467382373884,
"matched": 3931
},
"0.5": {
"precision": 0.11445159265651969,
"recall": 0.7844697784469779,
"f1": 0.19975899654926876,
"matched": 3647
}
},
"burst_start_mae_s": 0.11067613914747675,
"burst_end_mae_s": 0.20828025477707007,
"burst_matched_event_class_accuracy": 0.4456148946594806,
"burst_matched_event_class_n": 4082,
"limitations": "Oracle-span and predicted-span classification reported separately. Boundaries use fixed 0.5 onset threshold and native-feature interpolation; IoU matching uses Hungarian assignment.",
"split": "validation",
"phase": "gemini",
"domain": "Flash",
"split_scope": "Same Flash validation audio before/after; used to select tuned checkpoint"
}