mHuBERT-147-bashkort / vocab.json
AigizK's picture
Upload tokenizer
e6f2ad2 verified
raw
history blame contribute delete
466 Bytes
{
"[PAD]": 38,
"[UNK]": 37,
"|": 0,
"а": 1,
"б": 2,
"в": 3,
"г": 4,
"д": 5,
"ж": 6,
"з": 7,
"и": 8,
"й": 9,
"к": 10,
"л": 11,
"м": 12,
"н": 13,
"о": 14,
"п": 15,
"р": 16,
"с": 17,
"т": 18,
"у": 19,
"ф": 20,
"х": 21,
"ц": 22,
"ч": 23,
"ш": 24,
"щ": 25,
"ы": 26,
"э": 27,
"ғ": 28,
"ҙ": 29,
"ҡ": 30,
"ң": 31,
"ҫ": 32,
"ү": 33,
"һ": 34,
"ә": 35,
"ө": 36
}