mms-tts-ara / tokenizer.json
Xenova's picture
Xenova HF staff
Upload tokenizer.json
269f137
raw
history blame
No virus
2.49 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 39,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Lowercase"
},
{
"type": "Replace",
"pattern": {
"Regex": "[^\u0627\u0646\u0643\u0639\u0625\u063a\u0630\u0629\u0633\u0631\u0637\u062e\u062a\u062c\u0638\u064a\u062f\u2013\u0635\u062b\u0623\u0649\u0636\u062d\u0647 \u0621\u0622\u0628\u0648\u0645\u0644\u0634\u0642\u0632\u0624\u0641_\u0626]"
},
"content": ""
},
{
"type": "Strip",
"strip_left": true,
"strip_right": true
},
{
"type": "Replace",
"pattern": {
"Regex": "(?=.)|(?<!^)$"
},
"content": "\u0627"
}
]
},
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": null,
"model": {
"vocab": {
"\u0627": 0,
"\u0646": 1,
"\u0643": 2,
"\u0639": 3,
"\u0625": 4,
"\u063a": 5,
"\u0630": 6,
"\u0629": 7,
"\u0633": 8,
"\u0631": 9,
"\u0637": 10,
"\u062e": 11,
"\u062a": 12,
"\u062c": 13,
"\u0638": 14,
"\u064a": 15,
"\u062f": 16,
"\u2013": 17,
"\u0635": 18,
"\u062b": 19,
"\u0623": 20,
"\u0649": 21,
"\u0636": 22,
"\u062d": 23,
"\u0647": 24,
" ": 25,
"\u0621": 26,
"\u0622": 27,
"\u0628": 28,
"\u0648": 29,
"\u0645": 30,
"\u0644": 31,
"\u0634": 32,
"\u0642": 33,
"\u0632": 34,
"\u0624": 35,
"\u0641": 36,
"_": 37,
"\u0626": 38,
"<unk>": 39
}
}
}