ninada / config_v3.json
gnumanth's picture
Release Ninada v3.0: 24,000 Hz Studio Neural TTS, Unified Q8F16 ONNX & 6-Language Voice Banks
91953dd verified
Raw History Blame Contribute Delete
5.21 kB
{
"architecture": "Ninada-24k-StyleTTS2-PLBERT-iSTFTNet",
"version": "3.0.0",
"sample_rate": 24000,
"hop_length": 600,
"vocab_size": 178,
"retroflex_lateral_slot": 79,
"fp32_size_mb": 310.36,
"q8f16_size_mb": 78.91,
"pack_info": {
"converted_w8_initializers": 190,
"converted_fp16_initializers": 190,
"saved_mb": 231.48,
"size_mb": 78.91,
"pipeline": "W8A32_per_channel + FP16_heads (zero activation quantization)"
},
"onnx_file": "onnx/ninada_24k_q8f16.onnx",
"voices": {
"sa": {
"file": "voices/sa.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9304
},
"hi": {
"file": "voices/hi.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.93
},
"kn": {
"file": "voices/kn.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9312
},
"ta": {
"file": "voices/ta.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9418
},
"te": {
"file": "voices/te.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9603
},
"ml": {
"file": "voices/ml.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9511
},
"female": {
"file": "voices/female.bin",
"bytes": 522240,
"shape": [
510,
1,
256
],
"l2_norm_mean": 2.9688
}
},
"probes": {
"sa": {
"ipa": "dʰəɾmɐkʂˈeːtɾeː kʊɾʊkʂˈeːtɾeː səmɐʋˈeːtɑː jʊjˈʊtsɐʋəhᵊ ; mˈɑːmɐkɑːh pˈɑːɳɖɐʋɑːʃʧəɪʋə kɪmɐkˈʊɾʋɐtə sˈʌɲʤɐjə .",
"num_tokens": 110,
"duration_sec": 6.8,
"latency_ms": 1922.7,
"rtf": 0.2827,
"rms": 0.1104,
"peak": 0.6315
},
"hi": {
"ipa": "nəməstˈeː , ˈɑːʤ kˈɑː mˈɔːsəm bəhˈʊt əʧʧʰˈɑː hˈɛː ˈɔːɾ hˈʌm səbʰˈiː sˈɑːtʰ mɪləkˈʌɾ kʰˈʊʃ hˈɛː̃ .",
"num_tokens": 99,
"duration_sec": 5.725,
"latency_ms": 1601.62,
"rtf": 0.2798,
"rms": 0.1145,
"peak": 0.5825
},
"kn": {
"ipa": "nəmɐskˈɑːɾə , ˈɪndʊ bɛŋɡɐɭˈuːɾɪnɐllɪ həʋˈɑːmɑːnə tʊmbˈɑː ʧɛnnˈɑːɡɪdɛ .",
"num_tokens": 72,
"duration_sec": 4.75,
"latency_ms": 1368.43,
"rtf": 0.2881,
"rms": 0.1192,
"peak": 0.6739
},
"ta": {
"ipa": "ʋəɳˈʌkkɐm, ˈɪndɾʊ sɛnnˈʌɪjɪl ʋˈɑːnɪləɪ mɪɡɐʋˈʊm ɪnɪmˈʌɪjɑːɡə ˈʊɭɭɐðʊ , nˈʌndɾɪ .",
"num_tokens": 82,
"duration_sec": 5.4,
"latency_ms": 1525.79,
"rtf": 0.2826,
"rms": 0.1111,
"peak": 0.6402
},
"te": {
"ipa": "nəmɐskˈɑːɾəm, ˈiːɾoːʤʊ hˈʌɪdɐɾɑːbɑːdloː ʋˈɑːtɑːʋɐɾɐɳəm ʧˈɑːlɑː bˈɑːɡʊndɪ .",
"num_tokens": 76,
"duration_sec": 4.85,
"latency_ms": 1403.42,
"rtf": 0.2894,
"rms": 0.1166,
"peak": 0.5954
},
"ml": {
"ipa": "nəmɐskˈɑːɾəm, ˈɪnnə kˈeːɾɐɭɐttɪl ʋˈʌɭɐɾɛ nˈʌllə kˈɑːlɑːʋɐstʰɐjɑːɳə , nˈʌndɪ .",
"num_tokens": 79,
"duration_sec": 5.35,
"latency_ms": 1511.21,
"rtf": 0.2825,
"rms": 0.1173,
"peak": 0.6103
}
},
"vocab": {
";": 1,
":": 2,
",": 3,
".": 4,
"!": 5,
"?": 6,
"—": 9,
"…": 10,
"\"": 11,
"(": 12,
")": 13,
"“": 14,
"”": 15,
" ": 16,
"̃": 17,
"ʣ": 18,
"ʥ": 19,
"ʦ": 20,
"ʨ": 21,
"ᵝ": 22,
"ꭧ": 23,
"A": 24,
"I": 25,
"O": 31,
"Q": 33,
"S": 35,
"T": 36,
"W": 39,
"Y": 41,
"ᵊ": 42,
"a": 43,
"b": 44,
"c": 45,
"d": 46,
"e": 47,
"f": 48,
"h": 50,
"i": 51,
"j": 52,
"k": 53,
"l": 54,
"m": 55,
"n": 56,
"o": 57,
"p": 58,
"q": 59,
"r": 60,
"s": 61,
"t": 62,
"u": 63,
"v": 64,
"w": 65,
"x": 66,
"y": 67,
"z": 68,
"ɑ": 69,
"ɐ": 70,
"ɒ": 71,
"æ": 72,
"β": 75,
"ɔ": 76,
"ɕ": 77,
"ç": 78,
"ɭ": 79,
"ɖ": 80,
"ð": 81,
"ʤ": 82,
"ə": 83,
"ɚ": 85,
"ɛ": 86,
"ɜ": 87,
"ɟ": 90,
"ɡ": 92,
"ɥ": 99,
"ɨ": 101,
"ɪ": 102,
"ʝ": 103,
"ɯ": 110,
"ɰ": 111,
"ŋ": 112,
"ɳ": 113,
"ɲ": 114,
"ɴ": 115,
"ø": 116,
"ɸ": 118,
"θ": 119,
"œ": 120,
"ɹ": 123,
"ɾ": 125,
"ɻ": 126,
"ʁ": 128,
"ɽ": 129,
"ʂ": 130,
"ʃ": 131,
"ʈ": 132,
"ʧ": 133,
"ʊ": 135,
"ʋ": 136,
"ʌ": 138,
"ɣ": 139,
"ɤ": 140,
"χ": 142,
"ʎ": 143,
"ʒ": 147,
"ʔ": 148,
"ˈ": 156,
"ˌ": 157,
"ː": 158,
"ʰ": 162,
"ʲ": 164,
"↓": 169,
"→": 171,
"↗": 172,
"↘": 173,
"ᵻ": 177
}
}