mms-tts-yor / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
8d0976d
raw
history blame
2.39 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 43,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^|n\u00ed\u1ecdi\u00e0\u1eb9tarb\u00ecw\u0301l\u0300k\u00e1s\u00faogmy\u00f3puej\u00f2f\u1e63\u00e9d\u00e8\u00f9\u0144h\\-\u01f9\u2014' ]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "|"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"|": 0,
"n": 1,
"\u00ed": 2,
"\u1ecd": 3,
"i": 4,
"\u00e0": 5,
"\u1eb9": 6,
"t": 7,
"a": 8,
"r": 9,
"b": 10,
"\u00ec": 11,
"w": 12,
"\u0301": 13,
"l": 14,
"\u0300": 15,
"k": 16,
"\u00e1": 17,
"s": 18,
"\u00fa": 19,
"o": 20,
"g": 21,
"m": 22,
"y": 23,
"\u00f3": 24,
"p": 25,
"u": 26,
"e": 27,
"j": 28,
"\u00f2": 29,
"f": 30,
"\u1e63": 31,
"\u00e9": 32,
"d": 33,
"\u00e8": 34,
"\u00f9": 35,
"\u0144": 36,
"h": 37,
"-": 38,
"\u01f9": 39,
"\u2014": 40,
"'": 41,
" ": 42,
"<unk>": 43
}
}
}