ntsema's picture
Upload tokenizer
ce5ab5e
{
"[PAD]": 38,
"[UNK]": 37,
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"f": 6,
"h": 7,
"i": 8,
"j": 9,
"k": 10,
"l": 11,
"m": 12,
"n": 13,
"o": 14,
"p": 15,
"s": 16,
"t": 17,
"u": 18,
"v": 19,
"x": 20,
"y": 21,
"z": 22,
"|": 0,
"ç": 23,
"ø": 24,
"ŋ": 25,
"ɟ": 26,
"ɡ": 27,
"ɣ": 28,
"ɯ": 29,
"ɲ": 30,
"ɾ": 31,
"ʂ": 32,
"ʐ": 33,
"ʝ": 34,
"ː": 35,
"͡": 36
}