Kokoro-82M-v1.0-ONNX / tokenizer.json
Xenova's picture
Xenova HF staff
Update tokenizer.json
73d7339 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [],
"normalizer": {
"type": "Replace",
"pattern": {
"Regex": "[^$;:,.!?\u2014\u2026\"()\u201c\u201d \u0303\u02a3\u02a5\u02a6\u02a8\u1d5d\uab67AIOQSTWY\u1d4aabcdefhijklmnopqrstuvwxyz\u0251\u0250\u0252\u00e6\u03b2\u0254\u0255\u00e7\u0256\u00f0\u02a4\u0259\u025a\u025b\u025c\u025f\u0261\u0265\u0268\u026a\u029d\u026f\u0270\u014b\u0273\u0272\u0274\u00f8\u0278\u03b8\u0153\u0279\u027e\u027b\u0281\u027d\u0282\u0283\u0288\u02a7\u028a\u028b\u028c\u0263\u0264\u03c7\u028e\u0292\u0294\u02c8\u02cc\u02d0\u02b0\u02b2\u2193\u2192\u2197\u2198\u1d7b]"
},
"content": ""
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "$",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "$",
"type_id": 0
}
}
],
"special_tokens": {
"$": {
"id": "$",
"ids": [
0
],
"tokens": [
"$"
]
}
}
},
"decoder": null,
"model": {
"vocab": {
"$": 0,
";": 1,
":": 2,
",": 3,
".": 4,
"!": 5,
"?": 6,
"\u2014": 9,
"\u2026": 10,
"\"": 11,
"(": 12,
")": 13,
"\u201c": 14,
"\u201d": 15,
" ": 16,
"\u0303": 17,
"\u02a3": 18,
"\u02a5": 19,
"\u02a6": 20,
"\u02a8": 21,
"\u1d5d": 22,
"\uab67": 23,
"A": 24,
"I": 25,
"O": 31,
"Q": 33,
"S": 35,
"T": 36,
"W": 39,
"Y": 41,
"\u1d4a": 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,
"\u0251": 69,
"\u0250": 70,
"\u0252": 71,
"\u00e6": 72,
"\u03b2": 75,
"\u0254": 76,
"\u0255": 77,
"\u00e7": 78,
"\u0256": 80,
"\u00f0": 81,
"\u02a4": 82,
"\u0259": 83,
"\u025a": 85,
"\u025b": 86,
"\u025c": 87,
"\u025f": 90,
"\u0261": 92,
"\u0265": 99,
"\u0268": 101,
"\u026a": 102,
"\u029d": 103,
"\u026f": 110,
"\u0270": 111,
"\u014b": 112,
"\u0273": 113,
"\u0272": 114,
"\u0274": 115,
"\u00f8": 116,
"\u0278": 118,
"\u03b8": 119,
"\u0153": 120,
"\u0279": 123,
"\u027e": 125,
"\u027b": 126,
"\u0281": 128,
"\u027d": 129,
"\u0282": 130,
"\u0283": 131,
"\u0288": 132,
"\u02a7": 133,
"\u028a": 135,
"\u028b": 136,
"\u028c": 138,
"\u0263": 139,
"\u0264": 140,
"\u03c7": 142,
"\u028e": 143,
"\u0292": 147,
"\u0294": 148,
"\u02c8": 156,
"\u02cc": 157,
"\u02d0": 158,
"\u02b0": 162,
"\u02b2": 164,
"\u2193": 169,
"\u2192": 171,
"\u2197": 172,
"\u2198": 173,
"\u1d7b": 177
}
}
}