mesm-tts / config.json
mesmertech's picture
mesm-tts: ten tiny English voices (ONNX + pdn WebAssembly engine), inference, samples, benchmarks
931612f
Raw History Blame Contribute Delete
2.76 kB
{
"model_type": "mesm-tts",
"version": "1.0",
"sample_rate": 24000,
"n_token": 178,
"max_input_ids": 512,
"front_end": "misaki 0.9.4 English G2P (US), as Kokoro's KPipeline(lang_code='a'); eSpeak NG fallback for words outside its lexicon",
"interface": {
"inputs": {
"input_ids": "int64 [1, T]: [0] + phoneme ids + [0], T <= 512",
"speed": "float32 [1]: 1.0 = trained rate"
},
"outputs": {
"waveform": "float32 [1, samples] at 24 kHz"
}
},
"voices": "voices.json",
"architecture": {
"heart": {
"text_side": "phoneme encoder (shared-weight transformer) + duration / F0 / energy predictors + projection into the teacher's phonetic feature space (v2g: LSTM-free, streamable)",
"decoder": "AdaIN convolutional trunk + source-filter head (64-harmonic sine bank from F0 plus shaped noise, synthesised with one inverse STFT)",
"packing": "int4 (groups of 32) / int6 / int8 weights unpacked at session start; *_noint8 files run fp32 math, the others int8 matrix products with 7-bit weights"
},
"phonon_voices": {
"text_side": "phoneme encoder + duration / F0 / energy predictors + a content branch predicting the teacher codec's latent features",
"decoder": "AdaIN convolutional trunk + source-filter head (ConvNeXt 160 x 4 blocks; Edwin 256 x 6)",
"packing": "int4 / int6 / int8 weights unpacked at session start, fp32 math"
}
},
"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,
"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
}
}