ai-voice-cloning/models/tokenizers/japanese.json

564 lines
13 KiB
JSON
Executable File
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"version":"1.0",
"truncation":null,
"padding":null,
"normalizer":null,
"pre_tokenizer":{
"type":"Whitespace"
},
"post_processor":null,
"decoder":null,
"added_tokens":[
{
"id":0,
"special":true,
"content":"[STOP]",
"single_word":false,
"lstrip":false,
"rstrip":false,
"normalized":false
},
{
"id":1,
"special":true,
"content":"[UNK]",
"single_word":false,
"lstrip":false,
"rstrip":false,
"normalized":false
},
{
"id":2,
"special":true,
"content":"[SPACE]",
"single_word":false,
"lstrip":false,
"rstrip":false,
"normalized":false
}
],
"model":{
"type":"BPE",
"language": "ja",
"dropout":null,
"unk_token":"[UNK]",
"continuing_subword_prefix":null,
"end_of_word_suffix":null,
"fuse_unk":false,
"vocab":{
"[STOP]": 0,
"[UNK]": 1,
"[SPACE]": 2,
"":255,
"": 14,
"": 22,
"": 34,
"": 18,
"": 28,
"": 254,
"": 230,
"": 253,
"": 215,
"": 214,
"": 213,
"": 229,
"": 194,
"": 193,
"": 192,
"": 252,
"": 228,
"": 93,
"": 112,
"": 251,
"": 119,
"": 150,
"": 227,
"": 250,
"": 212,
"": 211,
"": 210,
"": 226,
"": 191,
"": 190,
"": 189,
"": 133,
"": 225,
"": 66,
"": 224,
"": 123,
"": 223,
"": 249,
"": 222,
"": 248,
"": 209,
"": 208,
"": 207,
"": 226,
"": 247,
"": 225,
"": 136,
"": 126,
"": 51,
"": 134,
"": 246,
"": 245,
"": 206,
"": 205,
"": 204,
"": 244,
"": 111,
"": 95,
"": 102,
"": 221,
"": 218,
"": 243,
"": 203,
"": 202,
"": 201,
"": 220,
"": 188,
"": 187,
"": 186,
"": 217,
"": 185,
"": 184,
"": 183,
"": 242,
"": 219,
"": 216,
"": 62,
"": 67,
"": 124,
"": 241,
"": 165,
"": 139,
"": 240,
"": 239,
"": 200,
"": 199,
"": 198,
"": 238,
"": 80,
"": 115,
"": 237,
"": 236,
"": 235,
"": 234,
"": 101,
"": 197,
"": 196,
"": 195,
"": 233,
"": 46,
"": 89,
"": 232,
"": 231,
"": 27,
"":182,
"":181,
"":180,
"":179,
"": 14,
"": 22,
"": 34,
"": 18,
"": 28,
"": 254,
"": 230,
"": 253,
"": 215,
"": 214,
"": 213,
"": 229,
"": 194,
"": 193,
"": 192,
"": 252,
"": 228,
"": 93,
"": 112,
"": 251,
"": 119,
"": 150,
"": 227,
"": 250,
"": 212,
"": 211,
"": 210,
"": 226,
"": 191,
"": 190,
"": 189,
"": 133,
"": 225,
"": 66,
"": 224,
"": 123,
"": 223,
"": 249,
"": 222,
"": 248,
"": 209,
"": 208,
"": 207,
"": 226,
"": 247,
"": 225,
"": 136,
"": 126,
"": 51,
"": 134,
"": 246,
"": 245,
"": 206,
"": 205,
"": 204,
"": 244,
"": 111,
"": 95,
"": 102,
"": 221,
"": 218,
"": 243,
"": 203,
"": 202,
"": 201,
"": 220,
"": 188,
"": 187,
"": 186,
"": 217,
"": 185,
"": 184,
"": 183,
"": 242,
"": 219,
"": 216,
"": 62,
"": 67,
"": 124,
"": 241,
"": 165,
"": 139,
"": 240,
"": 239,
"": 200,
"": 199,
"": 198,
"": 238,
"": 80,
"": 115,
"": 237,
"": 236,
"": 235,
"": 234,
"": 101,
"": 197,
"": 196,
"": 195,
"": 233,
"": 46,
"": 89,
"": 232,
"": 231,
"": 27,
"":182,
"":181,
"":180,
"":179,
"ba": 221,
"bi": 220,
"bu": 219,
"bya": 188,
"byo": 186,
"byu": 187,
"cha": 209,
"chi": 248,
"cho": 207,
"chu": 208,
"da": 222,
"fu": 242,
"ga": 230,
"gi": 229,
"gu": 228,
"gya": 194,
"gyo": 192,
"gyu": 193,
"hi": 243,
"ho": 241,
"hya": 203,
"hyo": 201,
"hyu": 202,
"ja": 191,
"ji": 226,
"jo": 189,
"ju": 190,
"ka": 254,
"ki": 253,
"ko": 251,
"ku": 252,
"kya": 215,
"kyo": 213,
"kyu": 214,
"ma": 240,
"mi": 239,
"mu": 238,
"mya": 200,
"myo": 198,
"myu": 199,
"na": 246,
"ni": 245,
"nu": 244,
"nya": 206,
"nyo": 204,
"nyu": 205,
"pa": 218,
"pi": 217,
"pu": 216,
"py": 183,
"pya": 185,
"pyu": 184,
"ra": 234,
"ru": 233,
"rya": 197,
"ryo": 195,
"ryu": 196,
"sha": 212,
"shi": 250,
"sho": 210,
"shu": 211,
"ta": 249,
"tsu": 247,
"wa": 232,
"wo": 231,
"ya": 237,
"yo": 235,
"yu": 236,
"za": 227,
"ze": 224,
"zo": 223,
"zu": 225,
"!": 3,
"'": 4,
"(": 5,
")": 6,
",": 7,
"": 7,
"-": 8,
".": 9,
"": 9,
"": 9,
"/": 10,
":": 11,
";": 12,
"?": 13,
"a": 14,
"b": 15,
"c": 16,
"d": 17,
"e": 18,
"f": 19,
"g": 20,
"h": 21,
"i": 22,
"j": 23,
"k": 24,
"l": 25,
"m": 26,
"n": 27,
"o": 28,
"p": 29,
"q": 30,
"r": 31,
"s": 32,
"t": 33,
"u": 34,
"v": 35,
"w": 36,
"x": 37,
"y": 38,
"z": 39,
"th": 40,
"in": 41,
"the": 42,
"an": 43,
"er": 44,
"ou": 45,
"re": 46,
"on": 47,
"at": 48,
"ed": 49,
"en": 50,
"to": 51,
"ing": 52,
"and": 53,
"is": 54,
"as": 55,
"al": 56,
"or": 57,
"of": 58,
"ar": 59,
"it": 60,
"es": 61,
"he": 62,
"st": 63,
"le": 64,
"om": 65,
"se": 66,
"be": 67,
"ad": 68,
"ow": 69,
"ly": 70,
"ch": 71,
"wh": 72,
"that": 73,
"you": 74,
"li": 75,
"ve": 76,
"ac": 77,
"ti": 78,
"ld": 79,
"me": 80,
"was": 81,
"gh": 82,
"id": 83,
"ll": 84,
"wi": 85,
"ent": 86,
"for": 87,
"ay": 88,
"ro": 89,
"ver": 90,
"ic": 91,
"her": 92,
"ke": 93,
"his": 94,
"no": 95,
"ut": 96,
"un": 97,
"ir": 98,
"lo": 99,
"we": 100,
"ri": 101,
"ha": 102,
"with": 103,
"ght": 104,
"out": 105,
"im": 106,
"ion": 107,
"all": 108,
"ab": 109,
"one": 110,
"ne": 111,
"ge": 112,
"ould": 113,
"ter": 114,
"mo": 115,
"had": 116,
"ce": 117,
"she": 118,
"go": 119,
"sh": 120,
"ur": 121,
"am": 122,
"so": 123,
"pe": 124,
"my": 125,
"de": 126,
"are": 127,
"but": 128,
"ome": 129,
"fr": 130,
"ther": 131,
"fe": 132,
"su": 133,
"do": 134,
"con": 135,
"te": 136,
"ain": 137,
"ere": 138,
"po": 139,
"if": 140,
"they": 141,
"us": 142,
"ag": 143,
"tr": 144,
"now": 145,
"oun": 146,
"this": 147,
"have": 148,
"not": 149,
"sa": 150,
"il": 151,
"up": 152,
"thing": 153,
"from": 154,
"ap": 155,
"him": 156,
"ack": 157,
"ation": 158,
"ant": 159,
"our": 160,
"op": 161,
"like": 162,
"ust": 163,
"ess": 164,
"bo": 165,
"ok": 166,
"ul": 167,
"ind": 168,
"ex": 169,
"com": 170,
"some": 171,
"there": 172,
"ers": 173,
"co": 174,
"res": 175,
"man": 176,
"ard": 177,
"pl": 178
},
"merges":[
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" ",
" "
]
}
}