mms-300m-sakha / vocab.json
volodya-leveryev's picture
Upload tokenizer
ee39f68
raw
history blame contribute delete
No virus
571 Bytes
{
"sah": {
"-": 34,
"<pad>": 39,
"<unk>": 38,
"y": 18,
"|": 17,
"а": 2,
"б": 24,
"в": 0,
"г": 36,
"д": 15,
"е": 29,
"ж": 19,
"з": 20,
"и": 25,
"й": 16,
"к": 33,
"л": 35,
"м": 8,
"н": 27,
"о": 11,
"п": 13,
"р": 23,
"с": 12,
"т": 1,
"у": 9,
"ф": 32,
"х": 14,
"ц": 6,
"ч": 26,
"ш": 31,
"щ": 10,
"ы": 37,
"ь": 30,
"э": 4,
"я": 21,
"ҕ": 22,
"ҥ": 28,
"ү": 5,
"һ": 7,
"ө": 3
}
}