Amasa5646's picture
Upload tokenizer
d4df4cc verified
raw
history blame
316 Bytes
{
"[PAD]": 27,
"[UNK]": 26,
"a": 1,
"b": 2,
"d": 3,
"e": 4,
"f": 5,
"g": 6,
"h": 7,
"i": 8,
"k": 9,
"l": 10,
"m": 11,
"n": 12,
"o": 13,
"p": 14,
"r": 15,
"s": 16,
"t": 17,
"u": 18,
"w": 19,
"y": 20,
"|": 0,
"á": 21,
"ɔ": 22,
"ɛ": 23,
"’": 24,
"•": 25
}