mms-tts-fra / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
e7953c6
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 44,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^\u00eez\\-\u00f9u\u00fby\u00e8xqcg\u00f4\u00ea_eidbaf\u0153hr\u00e9ksv\u00e0 \u2013p\u00ebtnoj\u00fc\u00e2\u00e7\u00ef'ml]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "\u00ee"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"\u00ee": 0,
"z": 1,
"-": 2,
"\u00f9": 3,
"u": 4,
"\u00fb": 5,
"y": 6,
"\u00e8": 7,
"x": 8,
"q": 9,
"c": 10,
"g": 11,
"\u00f4": 12,
"\u00ea": 13,
"_": 14,
"e": 15,
"i": 16,
"d": 17,
"b": 18,
"a": 19,
"f": 20,
"\u0153": 21,
"h": 22,
"r": 23,
"\u00e9": 24,
"k": 25,
"s": 26,
"v": 27,
"\u00e0": 28,
" ": 29,
"\u2013": 30,
"p": 31,
"\u00eb": 32,
"t": 33,
"n": 34,
"o": 35,
"j": 36,
"\u00fc": 37,
"\u00e2": 38,
"\u00e7": 39,
"\u00ef": 40,
"'": 41,
"m": 42,
"l": 43,
"<unk>": 44
}
}
}