mms-tts-eng / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
ac23080
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 38,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^k'zyudhesw\u20133cp\\-1jmi flo0bra42n_xvtq56g]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "k"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"k": 0,
"'": 1,
"z": 2,
"y": 3,
"u": 4,
"d": 5,
"h": 6,
"e": 7,
"s": 8,
"w": 9,
"\u2013": 10,
"3": 11,
"c": 12,
"p": 13,
"-": 14,
"1": 15,
"j": 16,
"m": 17,
"i": 18,
" ": 19,
"f": 20,
"l": 21,
"o": 22,
"0": 23,
"b": 24,
"r": 25,
"a": 26,
"4": 27,
"2": 28,
"n": 29,
"_": 30,
"x": 31,
"v": 32,
"t": 33,
"q": 34,
"5": 35,
"6": 36,
"g": 37,
"<unk>": 38
}
}
}