wav2vec2-base / vocab.json
HuyenNguyen's picture
Upload tokenizer
c90e785
{
"[PAD]": 90,
"[UNK]": 89,
"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,
"â": 25,
"ã": 26,
"è": 27,
"é": 28,
"ê": 29,
"ì": 30,
"í": 31,
"ò": 32,
"ó": 33,
"ô": 34,
"õ": 35,
"ù": 36,
"ú": 37,
"ý": 38,
"ă": 39,
"đ": 40,
"ĩ": 41,
"ũ": 42,
"ơ": 43,
"ư": 44,
"ạ": 45,
"ả": 46,
"ấ": 47,
"ầ": 48,
"ẩ": 49,
"ẫ": 50,
"ậ": 51,
"ắ": 52,
"ằ": 53,
"ẳ": 54,
"ẵ": 55,
"ặ": 56,
"ẹ": 57,
"ẻ": 58,
"ẽ": 59,
"ế": 60,
"ề": 61,
"ể": 62,
"ễ": 63,
"ệ": 64,
"ỉ": 65,
"ị": 66,
"ọ": 67,
"ỏ": 68,
"ố": 69,
"ồ": 70,
"ổ": 71,
"ỗ": 72,
"ộ": 73,
"ớ": 74,
"ờ": 75,
"ở": 76,
"ỡ": 77,
"ợ": 78,
"ụ": 79,
"ủ": 80,
"ứ": 81,
"ừ": 82,
"ử": 83,
"ữ": 84,
"ự": 85,
"ỳ": 86,
"ỷ": 87,
"ỹ": 88
}