CS_mms_eng_yor / vocab.json
oluwagbotty's picture
Upload tokenizer
9b0dddd verified
{
"eng_yor": {
"\n": 0,
"\f": 1,
"0": 3,
"1": 4,
"2": 5,
"3": 6,
"4": 7,
"5": 8,
"6": 9,
"7": 10,
"8": 11,
"9": 12,
"[PAD]": 65,
"[UNK]": 64,
"\\": 13,
"a": 14,
"b": 15,
"c": 16,
"d": 17,
"e": 18,
"f": 19,
"g": 20,
"h": 21,
"i": 22,
"j": 23,
"k": 24,
"l": 25,
"m": 26,
"n": 27,
"o": 28,
"p": 29,
"q": 30,
"r": 31,
"s": 32,
"t": 33,
"u": 34,
"v": 35,
"w": 36,
"x": 37,
"y": 38,
"z": 39,
"|": 2,
" ": 40,
"à": 41,
"á": 42,
"è": 43,
"é": 44,
"ì": 45,
"í": 46,
"î": 47,
"ñ": 48,
"ò": 49,
"ó": 50,
"ù": 51,
"ú": 52,
"ý": 53,
"ń": 54,
"ǹ": 55,
"̀": 56,
"́": 57,
"̣": 58,
"ṣ": 59,
"ẹ": 60,
"ọ": 61,
"’": 62,
"…": 63
}
}