wav2vec2-tokenizer / vocab.json
ms3c's picture
Upload tokenizer
e28e265
raw
history blame contribute delete
963 Bytes
{
"[PAD]": 78,
"[UNK]": 77,
"a": 1,
"b": 2,
"c": 3,
"d": 4,
"e": 5,
"g": 6,
"h": 7,
"i": 8,
"k": 9,
"l": 10,
"m": 11,
"n": 12,
"o": 13,
"p": 14,
"q": 15,
"r": 16,
"s": 17,
"t": 18,
"u": 19,
"v": 20,
"x": 21,
"y": 22,
"|": 0,
"à": 23,
"á": 24,
"ã": 25,
"ê": 26,
"ì": 27,
"ò": 28,
"õ": 29,
"ù": 30,
"ý": 31,
"ă": 32,
"đ": 33,
"ĩ": 34,
"ũ": 35,
"ơ": 36,
"ư": 37,
"ạ": 38,
"ả": 39,
"ấ": 40,
"ầ": 41,
"ẩ": 42,
"ẫ": 43,
"ậ": 44,
"ắ": 45,
"ẳ": 46,
"ặ": 47,
"ẹ": 48,
"ẻ": 49,
"ẽ": 50,
"ế": 51,
"ề": 52,
"ể": 53,
"ễ": 54,
"ệ": 55,
"ỉ": 56,
"ị": 57,
"ọ": 58,
"ỏ": 59,
"ố": 60,
"ồ": 61,
"ổ": 62,
"ộ": 63,
"ớ": 64,
"ờ": 65,
"ở": 66,
"ỡ": 67,
"ợ": 68,
"ụ": 69,
"ủ": 70,
"ứ": 71,
"ừ": 72,
"ử": 73,
"ữ": 74,
"ự": 75,
"ỳ": 76
}