Yakut-ASR / vocab.json
MatricariaV's picture
Upload tokenizer
4075225 verified
raw
history blame contribute delete
627 Bytes
{
"sah": {
"*": 0,
"[PAD]": 43,
"[UNK]": 42,
"o": 1,
"y": 2,
"ç": 3,
"а": 4,
"б": 5,
"в": 6,
"г": 7,
"д": 8,
"е": 9,
"ж": 10,
"з": 11,
"и": 12,
"й": 13,
"к": 14,
"л": 15,
"м": 16,
"н": 17,
"о": 18,
"п": 19,
"р": 20,
"с": 21,
"т": 22,
"у": 23,
"ф": 24,
"х": 25,
"ц": 26,
"ч": 27,
"ш": 28,
"щ": 29,
"ъ": 30,
"ы": 31,
"ь": 32,
"э": 33,
"ю": 34,
"я": 35,
"і": 36,
"ҕ": 37,
"ҥ": 38,
"ү": 39,
"һ": 40,
"ө": 41
}
}