mms-tts-por / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
7f3196e
{
"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": "[^\u00e0\u00fa1ul2h\u00e9p\u00e3x'\u00ea_s\u00e74vm\\-gqcz\u00e2\u00edteoifb r\u00f4n\u2014\u00f3ajd\u00f5\u00e1]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "\u00e0"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"\u00e0": 0,
"\u00fa": 1,
"1": 2,
"u": 3,
"l": 4,
"2": 5,
"h": 6,
"\u00e9": 7,
"p": 8,
"\u00e3": 9,
"x": 10,
"'": 11,
"\u00ea": 12,
"_": 13,
"s": 14,
"\u00e7": 15,
"4": 16,
"v": 17,
"m": 18,
"-": 19,
"g": 20,
"q": 21,
"c": 22,
"z": 23,
"\u00e2": 24,
"\u00ed": 25,
"t": 26,
"e": 27,
"o": 28,
"i": 29,
"f": 30,
"b": 31,
" ": 32,
"r": 33,
"\u00f4": 34,
"n": 35,
"\u2014": 36,
"\u00f3": 37,
"a": 38,
"j": 39,
"d": 40,
"\u00f5": 41,
"\u00e1": 42,
"<unk>": 43
}
}
}