asha_twi_adapter / vocab.json
pius-code's picture
Upload tokenizer
5b85f02 verified
Raw History Blame Contribute Delete
731 Bytes
{
"aka": {
")": 1,
"0": 2,
"3": 3,
"4": 4,
"5": 5,
"6": 6,
"[PAD]": 52,
"[UNK]": 51,
"a": 7,
"b": 8,
"c": 9,
"d": 10,
"e": 11,
"f": 12,
"g": 13,
"h": 14,
"i": 15,
"j": 16,
"k": 17,
"l": 18,
"m": 19,
"n": 20,
"o": 21,
"p": 22,
"q": 23,
"r": 24,
"s": 25,
"t": 26,
"u": 27,
"v": 28,
"w": 29,
"x": 30,
"y": 31,
"z": 32,
"|": 0,
"·": 33,
"á": 34,
"ã": 35,
"õ": 36,
"ĩ": 37,
"ũ": 38,
"ɔ": 39,
"ɛ": 40,
"ʹ": 41,
"́": 42,
"—": 43,
"‘": 44,
"’": 45,
"“": 46,
"•": 47,
"…": 48,
"ℇ": 49,
"ↄ": 50
}
}