uspanteko_asr / vocab.json
Robert Henderson
tokens, tokenizer, and vocab
24d8334
raw
history blame contribute delete
518 Bytes
{
"'": 6,
"1": 7,
"2": 23,
"5": 29,
"8": 31,
"9": 34,
"[PAD]": 45,
"[UNK]": 44,
"a": 8,
"b": 32,
"c": 16,
"d": 11,
"e": 18,
"f": 19,
"g": 22,
"h": 12,
"i": 5,
"j": 4,
"k": 10,
"l": 38,
"m": 25,
"n": 26,
"o": 9,
"p": 17,
"q": 43,
"r": 33,
"s": 35,
"t": 15,
"u": 1,
"v": 40,
"w": 28,
"x": 30,
"y": 0,
"z": 42,
"|": 20,
"´": 13,
"à": 41,
"á": 14,
"é": 36,
"ì": 2,
"í": 3,
"ñ": 24,
"ò": 37,
"ó": 39,
"ú": 21,
"ü": 27
}