mattbonnell's picture
Upload tokenizer
7f382cc verified
raw
history blame
543 Bytes
{
"[PAD]": 46,
"[UNK]": 45,
"a": 2,
"b": 42,
"d": 17,
"e": 12,
"f": 0,
"h": 39,
"i": 29,
"j": 1,
"k": 35,
"l": 23,
"m": 16,
"n": 44,
"o": 18,
"p": 21,
"s": 32,
"t": 4,
"u": 37,
"v": 6,
"w": 26,
"z": 9,
"|": 43,
"æ": 13,
"ð": 33,
"ŋ": 40,
"ɐ": 14,
"ɑ": 7,
"ɔ": 25,
"ə": 31,
"ɚ": 30,
"ɛ": 5,
"ɜ": 41,
"ɡ": 22,
"ɣ": 20,
"ɪ": 10,
"ɹ": 34,
"ɾ": 11,
"ʃ": 19,
"ʊ": 27,
"ʌ": 15,
"ʒ": 36,
"ʔ": 3,
"ː": 38,
"̩": 8,
"θ": 24,
"ᵻ": 28
}