mms-tts-udm / vocab.json
sanchit-gandhi's picture
Upload tokenizer
2b98eb5
raw
history blame contribute delete
495 Bytes
{
" ": 31,
"-": 12,
"_": 37,
"а": 23,
"б": 9,
"в": 0,
"г": 24,
"д": 22,
"е": 27,
"ж": 2,
"з": 40,
"и": 10,
"й": 4,
"к": 26,
"л": 15,
"м": 17,
"н": 36,
"о": 13,
"п": 16,
"р": 28,
"с": 35,
"т": 20,
"у": 8,
"ф": 38,
"х": 41,
"ц": 19,
"ч": 30,
"ш": 5,
"щ": 14,
"ъ": 39,
"ы": 32,
"ь": 33,
"э": 25,
"ю": 18,
"я": 1,
"ё": 29,
"ӝ": 11,
"ӟ": 6,
"ӥ": 3,
"ӧ": 34,
"ӵ": 7,
"–": 21
}