voxtream2-ru / phoneme_to_token.json
simba9's picture
VoXtream2-RU v10-DPO
dc067e9 verified
Raw
History Blame Contribute Delete
2.11 kB
{
"aɪ": 0,
"aɪə": 1,
"aɪɚ": 2,
"aʊ": 3,
"b": 4,
"d": 5,
"dʒ": 6,
"eɪ": 7,
"f": 8,
"h": 9,
"i": 10,
"iə": 11,
"iː": 12,
"j": 13,
"k": 14,
"l": 15,
"m": 16,
"n": 17,
"n̩": 18,
"oʊ": 19,
"oː": 20,
"oːɹ": 21,
"p": 22,
"r": 23,
"s": 24,
"t": 25,
"tʃ": 26,
"uː": 27,
"v": 28,
"w": 29,
"x": 30,
"z": 31,
"æ": 32,
"ð": 33,
"ŋ": 34,
"ɐ": 35,
"ɑː": 36,
"ɑːɹ": 37,
"ɔ": 38,
"ɔɪ": 39,
"ɔː": 40,
"ɔːɹ": 41,
"ə": 42,
"əl": 43,
"ɚ": 44,
"ɛ": 45,
"ɛɹ": 46,
"ɜː": 47,
"ɡ": 48,
"ɪ": 49,
"ɪɹ": 50,
"ɹ": 51,
"ɾ": 52,
"ʃ": 53,
"ʊ": 54,
"ʊɹ": 55,
"ʌ": 56,
"ʒ": 57,
"ʔ": 58,
"ˈaɪ": 59,
"ˈaɪə": 60,
"ˈaɪɚ": 61,
"ˈaʊ": 62,
"ˈeɪ": 63,
"ˈiə": 64,
"ˈiː": 65,
"ˈoʊ": 66,
"ˈoː": 67,
"ˈoːɹ": 68,
"ˈuː": 69,
"ˈæ": 70,
"ˈɑː": 71,
"ˈɑːɹ": 72,
"ˈɔ": 73,
"ˈɔɪ": 74,
"ˈɔː": 75,
"ˈɔːɹ": 76,
"ˈə": 77,
"ˈɚ": 78,
"ˈɛ": 79,
"ˈɛɹ": 80,
"ˈɛː": 81,
"ˈɜː": 82,
"ˈɪ": 83,
"ˈɪɹ": 84,
"ˈʊ": 85,
"ˈʊɹ": 86,
"ˈʌ": 87,
"ˌaɪ": 88,
"ˌaɪɚ": 89,
"ˌaʊ": 90,
"ˌeɪ": 91,
"ˌiə": 92,
"ˌiː": 93,
"ˌoʊ": 94,
"ˌoː": 95,
"ˌoːɹ": 96,
"ˌuː": 97,
"ˌæ": 98,
"ˌɐ": 99,
"ˌɑː": 100,
"ˌɑːɹ": 101,
"ˌɔ": 102,
"ˌɔɪ": 103,
"ˌɔː": 104,
"ˌɔːɹ": 105,
"ˌə": 106,
"ˌɛ": 107,
"ˌɛɹ": 108,
"ˌɜː": 109,
"ˌɪ": 110,
"ˌɪɹ": 111,
"ˌʊ": 112,
"ˌʊɹ": 113,
"ˌʌ": 114,
"θ": 115,
"ᵻ": 116,
".": 117,
",": 118,
"?": 119,
"sil": 120,
"!": 121,
"ˈɑ": 122,
"ˈo": 123,
"ɭ": 124,
"ˈe": 125,
"a": 126,
"ˈi": 127,
"tʲ": 128,
"nʲ": 129,
"y": 130,
"sʲ": 131,
"u": 132,
"ɭʲ": 133,
"rʲ": 134,
"ˈu": 135,
"tʃʲ": 136,
"ˈy": 137,
"dʲ": 138,
"mʲ": 139,
"vʲ": 140,
"ts": 141,
"ja": 142,
"kʲ": 143,
"ˈɵ": 144,
"ˈja": 145,
"pʲ": 146,
"bʲ": 147,
"ju": 148,
"ɕ": 149,
"o": 150,
"ʑ": 151,
"e": 152,
"ɡʲ": 153,
"ɑ": 154,
"ˈa": 155,
"fʲ": 156,
"ˈju": 157,
"ˌɑ": 158,
"ɵ": 159,
"dʒʲ": 160,
"ˌi": 161,
"ˌja": 162,
"unk": 163
}