mms-tts-deu / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
85dfcf4
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 45,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^ v2qg\\-f18ah4\u00f63rm\u00e4lnt\u00ebdby\u00dfou_js65\u00efci\u00fcpke\u2013wz7x0]"
},
"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,
"v": 1,
"2": 2,
"q": 3,
"g": 4,
"-": 5,
"f": 6,
"1": 7,
"8": 8,
"a": 9,
"h": 10,
"4": 11,
"\u00f6": 12,
"3": 13,
"r": 14,
"m": 15,
"\u00e4": 16,
"l": 17,
"n": 18,
"t": 19,
"\u00eb": 20,
"d": 21,
"b": 22,
"y": 23,
"\u00df": 24,
"o": 25,
"u": 26,
"_": 27,
"j": 28,
"s": 29,
"6": 30,
"5": 31,
"\u00ef": 32,
"c": 33,
"i": 34,
"\u00fc": 35,
"p": 36,
"k": 37,
"e": 38,
"\u2013": 39,
"w": 40,
"z": 41,
"7": 42,
"x": 43,
"0": 44,
"<unk>": 45
}
}
}