kokoro-kmp-models / validation /package-validation.json
Shusek00's picture
Correct recommended revision for prebuilt frontends v2.1.1
d0ad239 verified
Raw History Blame Contribute Delete
40.4 kB
{
"catalogVersion": "2.1.1",
"catalogSchemaValidated": true,
"onnxRuntimeVersion": "1.29.0",
"artifactsVerified": 183,
"modelsValidated": 4,
"languageProfilesValidated": 11,
"voicesValidated": 159,
"frontendCasesValidated": 12,
"frontendOnnxModelsValidated": 9,
"frontendOnnxSmokeTests": [
{"language": "en-us", "path": "phonemizers/en-us/phonemizer_en_us.onnx", "sha256": "479cd9d89819a60c4f8609dbb116ae5b362d46c0c592b97605968cbaef1e7bc6", "logitsShape": [1, 2, 116]},
{"language": "en-gb", "path": "phonemizers/en-gb/phonemizer_en_gb.onnx", "sha256": "065baba624db8391905e53c78706a12c5f4cba12a77e62a90900b2113bdb17e7", "logitsShape": [1, 2, 116]},
{"language": "es", "path": "phonemizers/es/phonemizer_es.onnx", "sha256": "0437232bb50cffdefc51995dc8195c14992b185655e3bc0f0005b97a7f162240", "logitsShape": [1, 2, 116]},
{"language": "fr", "path": "phonemizers/fr/phonemizer_fr.onnx", "sha256": "d0ca22d75569827f86d73bd8f071a128e478d4f6f107e94035236ba080658485", "logitsShape": [1, 2, 116]},
{"language": "hi", "path": "phonemizers/hi/phonemizer_hi.onnx", "sha256": "7e046cd695d2615bad723b24e7fbe0339594526f6953df4c5d20aa53862a9678", "logitsShape": [1, 2, 116]},
{"language": "it", "path": "phonemizers/it/phonemizer_it.onnx", "sha256": "30c115355c28c1c8657eba91a1557d89b9bb69b373202399546719cf2991f9f8", "logitsShape": [1, 2, 116]},
{"language": "pt", "path": "phonemizers/pt-br/phonemizer_pt.onnx", "sha256": "fb30ed5fbdf2465b5f3d8a08903d2cc50dfa77b4c4c24518ac0ba26640393f52", "logitsShape": [1, 2, 116]},
{"language": "pl", "path": "phonemizers/pl/phonemizer_pl.onnx", "sha256": "4cdbafd810ed3cad701c24380894115f848cfa39602d731e7a8e085adee62233", "logitsShape": [1, 2, 116]},
{"language": "de", "path": "phonemizers/de/phonemizer_de.onnx", "sha256": "aef1d8a6163b426733059f35f406c540ccd08a3f7855eebe6a09ab4908d5dac7", "logitsShape": [1, 2, 116]}
],
"cases": [
{
"id": "en-us-af-heart",
"language": "en-us",
"voice": "af_heart",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 13,
"inputTokens": 15,
"outputSamples": 37800,
"durationSeconds": 1.575,
"peakAbsoluteAmplitude": 0.314272940158844
},
{
"id": "en-us-af-maple-v1.1",
"language": "en-us",
"voice": "af_maple",
"modelId": "kokoro-v1.1-zh-fp32",
"phonemeCodePoints": 13,
"inputTokens": 15,
"outputSamples": 44400,
"durationSeconds": 1.85,
"peakAbsoluteAmplitude": 0.21911364793777466
},
{
"id": "en-gb-bf-emma",
"language": "en-gb",
"voice": "bf_emma",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 13,
"inputTokens": 15,
"outputSamples": 42600,
"durationSeconds": 1.775,
"peakAbsoluteAmplitude": 0.3721811771392822
},
{
"id": "es-ef-dora",
"language": "es",
"voice": "ef_dora",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 12,
"inputTokens": 14,
"outputSamples": 26400,
"durationSeconds": 1.1,
"peakAbsoluteAmplitude": 0.3340049088001251
},
{
"id": "fr-ff-siwis",
"language": "fr",
"voice": "ff_siwis",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 18,
"inputTokens": 20,
"outputSamples": 43200,
"durationSeconds": 1.8,
"peakAbsoluteAmplitude": 0.4996577799320221
},
{
"id": "hi-hf-alpha",
"language": "hi",
"voice": "hf_alpha",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 20,
"inputTokens": 22,
"outputSamples": 51600,
"durationSeconds": 2.15,
"peakAbsoluteAmplitude": 0.5127443671226501
},
{
"id": "it-if-sara",
"language": "it",
"voice": "if_sara",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 12,
"inputTokens": 14,
"outputSamples": 37200,
"durationSeconds": 1.55,
"peakAbsoluteAmplitude": 0.6955161690711975
},
{
"id": "ja-jf-alpha",
"language": "ja",
"voice": "jf_alpha",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 17,
"inputTokens": 19,
"outputSamples": 48600,
"durationSeconds": 2.025,
"peakAbsoluteAmplitude": 0.34626448154449463
},
{
"id": "pt-br-pf-dora",
"language": "pt-br",
"voice": "pf_dora",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 13,
"inputTokens": 15,
"outputSamples": 27600,
"durationSeconds": 1.15,
"peakAbsoluteAmplitude": 0.36317700147628784
},
{
"id": "zh-zf-001-v1.1",
"language": "zh",
"voice": "zf_001",
"modelId": "kokoro-v1.1-zh-fp32",
"phonemeCodePoints": 15,
"inputTokens": 17,
"outputSamples": 48600,
"durationSeconds": 2.025,
"peakAbsoluteAmplitude": 0.4433383345603943
},
{
"id": "zh-zf-xiaoxiao-v1.0",
"language": "zh",
"voice": "zf_xiaoxiao",
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 17,
"inputTokens": 19,
"outputSamples": 49800,
"durationSeconds": 2.075,
"peakAbsoluteAmplitude": 0.5633978843688965
},
{
"id": "pl-pm-mateusz",
"language": "pl",
"voice": "pm_mateusz",
"modelId": "kokoro-pl-fp32",
"phonemeCodePoints": 24,
"inputTokens": 26,
"outputSamples": 49200,
"durationSeconds": 2.05,
"peakAbsoluteAmplitude": 0.24498526751995087
},
{
"id": "de-df-anna",
"language": "de",
"voice": "df_anna",
"modelId": "kokoro-de-fp32",
"phonemeCodePoints": 13,
"inputTokens": 15,
"outputSamples": 34200,
"durationSeconds": 1.425,
"peakAbsoluteAmplitude": 0.2567141056060791
}
],
"voiceSmokeTests": [
{
"language": "en-us",
"voice": "af_alloy",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.40653708577156067
},
{
"language": "en-us",
"voice": "af_aoede",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.3163083791732788
},
{
"language": "en-us",
"voice": "af_bella",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.13664785027503967
},
{
"language": "en-us",
"voice": "af_heart",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.22153674066066742
},
{
"language": "en-us",
"voice": "af_jessica",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12000,
"peakAbsoluteAmplitude": 0.327208936214447
},
{
"language": "en-us",
"voice": "af_kore",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.17504380643367767
},
{
"language": "en-us",
"voice": "af_maple",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 32400,
"peakAbsoluteAmplitude": 0.16933174431324005
},
{
"language": "en-us",
"voice": "af_nicole",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.5175233483314514
},
{
"language": "en-us",
"voice": "af_nova",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.14568452537059784
},
{
"language": "en-us",
"voice": "af_river",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.49193358421325684
},
{
"language": "en-us",
"voice": "af_sarah",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.4663853645324707
},
{
"language": "en-us",
"voice": "af_sky",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16200,
"peakAbsoluteAmplitude": 0.38015830516815186
},
{
"language": "en-us",
"voice": "af_sol",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 31200,
"peakAbsoluteAmplitude": 0.30626776814460754
},
{
"language": "en-us",
"voice": "am_adam",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.5502600073814392
},
{
"language": "en-us",
"voice": "am_echo",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.44180822372436523
},
{
"language": "en-us",
"voice": "am_eric",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 10800,
"peakAbsoluteAmplitude": 0.3035421371459961
},
{
"language": "en-us",
"voice": "am_fenrir",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.442539244890213
},
{
"language": "en-us",
"voice": "am_liam",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.39362677931785583
},
{
"language": "en-us",
"voice": "am_michael",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.20319819450378418
},
{
"language": "en-us",
"voice": "am_onyx",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.4561375081539154
},
{
"language": "en-us",
"voice": "am_puck",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 21000,
"peakAbsoluteAmplitude": 0.4743620455265045
},
{
"language": "en-us",
"voice": "am_santa",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.4820050895214081
},
{
"language": "en-gb",
"voice": "bf_alice",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.5165678262710571
},
{
"language": "en-gb",
"voice": "bf_emma",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.30898332595825195
},
{
"language": "en-gb",
"voice": "bf_isabella",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.42079681158065796
},
{
"language": "en-gb",
"voice": "bf_lily",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.3620645999908447
},
{
"language": "en-gb",
"voice": "bf_vale",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 31200,
"peakAbsoluteAmplitude": 0.1745903193950653
},
{
"language": "en-gb",
"voice": "bm_daniel",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12000,
"peakAbsoluteAmplitude": 0.30079784989356995
},
{
"language": "en-gb",
"voice": "bm_fable",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12000,
"peakAbsoluteAmplitude": 0.27494528889656067
},
{
"language": "en-gb",
"voice": "bm_george",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.2728273570537567
},
{
"language": "en-gb",
"voice": "bm_lewis",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.2729092240333557
},
{
"language": "es",
"voice": "ef_dora",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 7800,
"peakAbsoluteAmplitude": 0.3438640236854553
},
{
"language": "es",
"voice": "em_alex",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 8400,
"peakAbsoluteAmplitude": 0.397594690322876
},
{
"language": "es",
"voice": "em_santa",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 7800,
"peakAbsoluteAmplitude": 0.3917274475097656
},
{
"language": "fr",
"voice": "ff_siwis",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.30524423718452454
},
{
"language": "hi",
"voice": "hf_alpha",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.6884216070175171
},
{
"language": "hi",
"voice": "hf_beta",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 1.4256104230880737
},
{
"language": "hi",
"voice": "hm_omega",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 2.406914234161377
},
{
"language": "hi",
"voice": "hm_psi",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 16200,
"peakAbsoluteAmplitude": 0.5316904783248901
},
{
"language": "it",
"voice": "if_sara",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.7542451620101929
},
{
"language": "it",
"voice": "im_nicola",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 12000,
"peakAbsoluteAmplitude": 0.46500882506370544
},
{
"language": "ja",
"voice": "jf_alpha",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.19610024988651276
},
{
"language": "ja",
"voice": "jf_gongitsune",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 21600,
"peakAbsoluteAmplitude": 0.24526211619377136
},
{
"language": "ja",
"voice": "jf_nezumi",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 18000,
"peakAbsoluteAmplitude": 0.15609341859817505
},
{
"language": "ja",
"voice": "jf_tebukuro",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 17400,
"peakAbsoluteAmplitude": 0.20058149099349976
},
{
"language": "ja",
"voice": "jm_kumo",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 11400,
"peakAbsoluteAmplitude": 0.38223984837532043
},
{
"language": "pt-br",
"voice": "pf_dora",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 8400,
"peakAbsoluteAmplitude": 0.3795718252658844
},
{
"language": "pt-br",
"voice": "pm_alex",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 9000,
"peakAbsoluteAmplitude": 0.4056200683116913
},
{
"language": "pt-br",
"voice": "pm_santa",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 9000,
"peakAbsoluteAmplitude": 0.3983622193336487
},
{
"language": "zh",
"voice": "zf_001",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.23955535888671875
},
{
"language": "zh",
"voice": "zf_002",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.24074937403202057
},
{
"language": "zh",
"voice": "zf_003",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.2986932694911957
},
{
"language": "zh",
"voice": "zf_004",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.19893479347229004
},
{
"language": "zh",
"voice": "zf_005",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.17709223926067352
},
{
"language": "zh",
"voice": "zf_006",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.22031813859939575
},
{
"language": "zh",
"voice": "zf_007",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.21045507490634918
},
{
"language": "zh",
"voice": "zf_008",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.2964230477809906
},
{
"language": "zh",
"voice": "zf_017",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.2112424373626709
},
{
"language": "zh",
"voice": "zf_018",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27600,
"peakAbsoluteAmplitude": 0.22922717034816742
},
{
"language": "zh",
"voice": "zf_019",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.2291719615459442
},
{
"language": "zh",
"voice": "zf_021",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.24013005197048187
},
{
"language": "zh",
"voice": "zf_022",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27600,
"peakAbsoluteAmplitude": 0.3359830379486084
},
{
"language": "zh",
"voice": "zf_023",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.22765442728996277
},
{
"language": "zh",
"voice": "zf_024",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 22200,
"peakAbsoluteAmplitude": 0.2716064751148224
},
{
"language": "zh",
"voice": "zf_026",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.22110140323638916
},
{
"language": "zh",
"voice": "zf_027",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.3019619882106781
},
{
"language": "zh",
"voice": "zf_028",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.1910015493631363
},
{
"language": "zh",
"voice": "zf_032",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.25031548738479614
},
{
"language": "zh",
"voice": "zf_036",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.1825103908777237
},
{
"language": "zh",
"voice": "zf_038",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.17004728317260742
},
{
"language": "zh",
"voice": "zf_039",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 29400,
"peakAbsoluteAmplitude": 0.19761449098587036
},
{
"language": "zh",
"voice": "zf_040",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.29859843850135803
},
{
"language": "zh",
"voice": "zf_042",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 19800,
"peakAbsoluteAmplitude": 0.17181207239627838
},
{
"language": "zh",
"voice": "zf_043",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.1853313446044922
},
{
"language": "zh",
"voice": "zf_044",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.23998628556728363
},
{
"language": "zh",
"voice": "zf_046",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28800,
"peakAbsoluteAmplitude": 0.2672297954559326
},
{
"language": "zh",
"voice": "zf_047",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.24551156163215637
},
{
"language": "zh",
"voice": "zf_048",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 29400,
"peakAbsoluteAmplitude": 0.27705711126327515
},
{
"language": "zh",
"voice": "zf_049",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28800,
"peakAbsoluteAmplitude": 0.2217119038105011
},
{
"language": "zh",
"voice": "zf_051",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 18000,
"peakAbsoluteAmplitude": 0.1782708764076233
},
{
"language": "zh",
"voice": "zf_059",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.21708674728870392
},
{
"language": "zh",
"voice": "zf_060",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 25200,
"peakAbsoluteAmplitude": 0.27887991070747375
},
{
"language": "zh",
"voice": "zf_067",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 17400,
"peakAbsoluteAmplitude": 0.1944415420293808
},
{
"language": "zh",
"voice": "zf_070",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.22100673615932465
},
{
"language": "zh",
"voice": "zf_071",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 29400,
"peakAbsoluteAmplitude": 0.2669046223163605
},
{
"language": "zh",
"voice": "zf_072",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.15065307915210724
},
{
"language": "zh",
"voice": "zf_073",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.28115636110305786
},
{
"language": "zh",
"voice": "zf_074",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 26400,
"peakAbsoluteAmplitude": 0.2154153287410736
},
{
"language": "zh",
"voice": "zf_075",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 33000,
"peakAbsoluteAmplitude": 0.25420287251472473
},
{
"language": "zh",
"voice": "zf_076",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 25200,
"peakAbsoluteAmplitude": 0.20031321048736572
},
{
"language": "zh",
"voice": "zf_077",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 24600,
"peakAbsoluteAmplitude": 0.1699475795030594
},
{
"language": "zh",
"voice": "zf_078",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27600,
"peakAbsoluteAmplitude": 0.2362118363380432
},
{
"language": "zh",
"voice": "zf_079",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27000,
"peakAbsoluteAmplitude": 0.27906665205955505
},
{
"language": "zh",
"voice": "zf_083",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 25200,
"peakAbsoluteAmplitude": 0.245240718126297
},
{
"language": "zh",
"voice": "zf_084",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 32400,
"peakAbsoluteAmplitude": 0.1513064205646515
},
{
"language": "zh",
"voice": "zf_085",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 37200,
"peakAbsoluteAmplitude": 0.16417743265628815
},
{
"language": "zh",
"voice": "zf_086",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27000,
"peakAbsoluteAmplitude": 0.21662725508213043
},
{
"language": "zh",
"voice": "zf_087",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27000,
"peakAbsoluteAmplitude": 0.257027268409729
},
{
"language": "zh",
"voice": "zf_088",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 22200,
"peakAbsoluteAmplitude": 0.13836441934108734
},
{
"language": "zh",
"voice": "zf_090",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 22200,
"peakAbsoluteAmplitude": 0.17676040530204773
},
{
"language": "zh",
"voice": "zf_092",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.15848815441131592
},
{
"language": "zh",
"voice": "zf_093",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 16800,
"peakAbsoluteAmplitude": 0.18749289214611053
},
{
"language": "zh",
"voice": "zf_094",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27600,
"peakAbsoluteAmplitude": 0.2506563365459442
},
{
"language": "zh",
"voice": "zf_099",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.18069329857826233
},
{
"language": "zh",
"voice": "zf_xiaobei",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 22800,
"peakAbsoluteAmplitude": 0.1947079300880432
},
{
"language": "zh",
"voice": "zf_xiaoni",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 22800,
"peakAbsoluteAmplitude": 0.2457195371389389
},
{
"language": "zh",
"voice": "zf_xiaoxiao",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 19800,
"peakAbsoluteAmplitude": 0.3716725707054138
},
{
"language": "zh",
"voice": "zf_xiaoyi",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 22200,
"peakAbsoluteAmplitude": 0.3965284824371338
},
{
"language": "zh",
"voice": "zm_009",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.2933622896671295
},
{
"language": "zh",
"voice": "zm_010",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.2294243425130844
},
{
"language": "zh",
"voice": "zm_011",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.21950319409370422
},
{
"language": "zh",
"voice": "zm_012",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.27849698066711426
},
{
"language": "zh",
"voice": "zm_013",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 12600,
"peakAbsoluteAmplitude": 0.20517835021018982
},
{
"language": "zh",
"voice": "zm_014",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 14400,
"peakAbsoluteAmplitude": 0.2106841504573822
},
{
"language": "zh",
"voice": "zm_015",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13200,
"peakAbsoluteAmplitude": 0.2438172698020935
},
{
"language": "zh",
"voice": "zm_016",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.18290100991725922
},
{
"language": "zh",
"voice": "zm_020",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 20400,
"peakAbsoluteAmplitude": 0.2841041088104248
},
{
"language": "zh",
"voice": "zm_025",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 23400,
"peakAbsoluteAmplitude": 0.3623069226741791
},
{
"language": "zh",
"voice": "zm_029",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.44700977206230164
},
{
"language": "zh",
"voice": "zm_030",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 25800,
"peakAbsoluteAmplitude": 0.3100058436393738
},
{
"language": "zh",
"voice": "zm_031",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 24600,
"peakAbsoluteAmplitude": 0.5345324277877808
},
{
"language": "zh",
"voice": "zm_033",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 18000,
"peakAbsoluteAmplitude": 0.4631604850292206
},
{
"language": "zh",
"voice": "zm_034",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.1575707197189331
},
{
"language": "zh",
"voice": "zm_035",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 21000,
"peakAbsoluteAmplitude": 0.318749338388443
},
{
"language": "zh",
"voice": "zm_037",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 30000,
"peakAbsoluteAmplitude": 0.5570223927497864
},
{
"language": "zh",
"voice": "zm_041",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.23820383846759796
},
{
"language": "zh",
"voice": "zm_045",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 16200,
"peakAbsoluteAmplitude": 0.24851448833942413
},
{
"language": "zh",
"voice": "zm_050",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 20400,
"peakAbsoluteAmplitude": 0.25350382924079895
},
{
"language": "zh",
"voice": "zm_052",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.25999271869659424
},
{
"language": "zh",
"voice": "zm_053",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.2532203793525696
},
{
"language": "zh",
"voice": "zm_054",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.1773664951324463
},
{
"language": "zh",
"voice": "zm_055",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 26400,
"peakAbsoluteAmplitude": 0.2680859863758087
},
{
"language": "zh",
"voice": "zm_056",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 19800,
"peakAbsoluteAmplitude": 0.23625126481056213
},
{
"language": "zh",
"voice": "zm_057",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 23400,
"peakAbsoluteAmplitude": 0.24460920691490173
},
{
"language": "zh",
"voice": "zm_058",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.1826353222131729
},
{
"language": "zh",
"voice": "zm_061",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 30600,
"peakAbsoluteAmplitude": 0.2989325523376465
},
{
"language": "zh",
"voice": "zm_062",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 29400,
"peakAbsoluteAmplitude": 0.23488964140415192
},
{
"language": "zh",
"voice": "zm_063",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 22800,
"peakAbsoluteAmplitude": 0.3629308342933655
},
{
"language": "zh",
"voice": "zm_064",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27000,
"peakAbsoluteAmplitude": 0.413673996925354
},
{
"language": "zh",
"voice": "zm_065",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 27000,
"peakAbsoluteAmplitude": 0.2893393337726593
},
{
"language": "zh",
"voice": "zm_066",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 17400,
"peakAbsoluteAmplitude": 0.1782597154378891
},
{
"language": "zh",
"voice": "zm_068",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28800,
"peakAbsoluteAmplitude": 0.34502434730529785
},
{
"language": "zh",
"voice": "zm_069",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.3046194314956665
},
{
"language": "zh",
"voice": "zm_080",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 17400,
"peakAbsoluteAmplitude": 0.2260209321975708
},
{
"language": "zh",
"voice": "zm_081",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 30000,
"peakAbsoluteAmplitude": 0.28944990038871765
},
{
"language": "zh",
"voice": "zm_082",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.42188143730163574
},
{
"language": "zh",
"voice": "zm_089",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 28200,
"peakAbsoluteAmplitude": 0.25824403762817383
},
{
"language": "zh",
"voice": "zm_091",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 24600,
"peakAbsoluteAmplitude": 0.30636465549468994
},
{
"language": "zh",
"voice": "zm_095",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15000,
"peakAbsoluteAmplitude": 0.26197656989097595
},
{
"language": "zh",
"voice": "zm_096",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.21767741441726685
},
{
"language": "zh",
"voice": "zm_097",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 15600,
"peakAbsoluteAmplitude": 0.2360699325799942
},
{
"language": "zh",
"voice": "zm_098",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 31200,
"peakAbsoluteAmplitude": 0.3175937533378601
},
{
"language": "zh",
"voice": "zm_100",
"modelId": "kokoro-v1.1-zh-fp32",
"inputTokens": 3,
"outputSamples": 16200,
"peakAbsoluteAmplitude": 0.25542011857032776
},
{
"language": "zh",
"voice": "zm_yunjian",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 18000,
"peakAbsoluteAmplitude": 0.15362043678760529
},
{
"language": "zh",
"voice": "zm_yunxi",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 25800,
"peakAbsoluteAmplitude": 0.1724967509508133
},
{
"language": "zh",
"voice": "zm_yunxia",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 21000,
"peakAbsoluteAmplitude": 0.24030020833015442
},
{
"language": "zh",
"voice": "zm_yunyang",
"modelId": "kokoro-v1.0-fp32",
"inputTokens": 3,
"outputSamples": 19200,
"peakAbsoluteAmplitude": 0.1682424545288086
},
{
"language": "pl",
"voice": "pm_mateusz",
"modelId": "kokoro-pl-fp32",
"inputTokens": 3,
"outputSamples": 13800,
"peakAbsoluteAmplitude": 0.16262945532798767
},
{
"language": "de",
"voice": "df_anna",
"modelId": "kokoro-de-fp32",
"inputTokens": 3,
"outputSamples": 16200,
"peakAbsoluteAmplitude": 0.16440598666667938
}
],
"boundaryCases": [
{
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 1,
"inputTokens": 3,
"outputSamples": 12600
},
{
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 128,
"inputTokens": 130,
"outputSamples": 251400
},
{
"modelId": "kokoro-v1.0-fp32",
"phonemeCodePoints": 510,
"inputTokens": 512,
"outputSamples": 657600
},
{
"modelId": "kokoro-v1.1-zh-fp32",
"phonemeCodePoints": 1,
"inputTokens": 3,
"outputSamples": 32400
},
{
"modelId": "kokoro-v1.1-zh-fp32",
"phonemeCodePoints": 128,
"inputTokens": 130,
"outputSamples": 210000
},
{
"modelId": "kokoro-v1.1-zh-fp32",
"phonemeCodePoints": 510,
"inputTokens": 512,
"outputSamples": 476400
},
{
"modelId": "kokoro-pl-fp32",
"phonemeCodePoints": 1,
"inputTokens": 3,
"outputSamples": 13800
},
{
"modelId": "kokoro-pl-fp32",
"phonemeCodePoints": 128,
"inputTokens": 130,
"outputSamples": 177600
},
{
"modelId": "kokoro-pl-fp32",
"phonemeCodePoints": 510,
"inputTokens": 512,
"outputSamples": 616800
},
{
"modelId": "kokoro-de-fp32",
"phonemeCodePoints": 1,
"inputTokens": 3,
"outputSamples": 16200
},
{
"modelId": "kokoro-de-fp32",
"phonemeCodePoints": 128,
"inputTokens": 130,
"outputSamples": 79800
},
{
"modelId": "kokoro-de-fp32",
"phonemeCodePoints": 510,
"inputTokens": 512,
"outputSamples": 307200
}
]
}