test_mms / vocab.json
oluwagbotty's picture
Upload tokenizer
70846b1 verified
raw
history blame contribute delete
825 Bytes
{
"eng_yor": {
"\f": 0,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"[PAD]": 59,
"[UNK]": 58,
"a": 12,
"b": 13,
"c": 14,
"d": 15,
"e": 16,
"f": 17,
"g": 18,
"h": 19,
"i": 20,
"j": 21,
"k": 22,
"l": 23,
"m": 24,
"n": 25,
"o": 26,
"p": 27,
"q": 28,
"r": 29,
"s": 30,
"t": 31,
"u": 32,
"v": 33,
"w": 34,
"x": 35,
"y": 36,
"z": 37,
"|": 1,
" ": 38,
"à": 39,
"á": 40,
"è": 41,
"é": 42,
"ì": 43,
"í": 44,
"î": 45,
"ñ": 46,
"ò": 47,
"ó": 48,
"ù": 49,
"ú": 50,
"ń": 51,
"̀": 52,
"́": 53,
"ṣ": 54,
"ẹ": 55,
"ọ": 56,
"’": 57
}
}