wav2vec2vncskh / vocab.json
infi
Upload tokenizer
8bc3371
{
"%": 33,
",": 69,
".": 3,
"0": 56,
"1": 64,
"2": 10,
"3": 0,
"4": 85,
"5": 101,
"6": 65,
"7": 57,
"8": 49,
"9": 4,
"[PAD]": 105,
"[UNK]": 104,
"a": 32,
"b": 14,
"c": 83,
"d": 25,
"e": 17,
"f": 93,
"g": 46,
"h": 45,
"i": 54,
"k": 108,
"l": 62,
"m": 29,
"n": 30,
"o": 47,
"p": 100,
"q": 68,
"r": 7,
"s": 76,
"t": 67,
"u": 82,
"v": 87,
"w": 60,
"x": 6,
"y": 12,
"z": 53,
"à": 26,
"á": 61,
"â": 63,
"ã": 55,
"è": 59,
"é": 66,
"ê": 20,
"ì": 51,
"í": 18,
"ò": 15,
"ó": 38,
"ô": 58,
"õ": 106,
"ù": 23,
"ú": 43,
"ý": 24,
"ă": 104,
"đ": 1,
"ĩ": 84,
"ũ": 16,
"ơ": 21,
"ư": 44,
"ạ": 88,
"ả": 96,
"ấ": 52,
"ầ": 78,
"ẩ": 71,
"ẫ": 86,
"ậ": 28,
"ắ": 107,
"ằ": 8,
"ẳ": 92,
"ẵ": 22,
"ặ": 97,
"ẹ": 74,
"ẻ": 95,
"ẽ": 72,
"ế": 81,
"ề": 41,
"ể": 11,
"ễ": 77,
"ệ": 75,
"ỉ": 42,
"ị": 2,
"ọ": 90,
"ỏ": 36,
"ố": 99,
"ồ": 19,
"ổ": 103,
"ỗ": 73,
"ộ": 39,
"ớ": 80,
"ờ": 9,
"ở": 91,
"ỡ": 34,
"ợ": 40,
"ụ": 37,
"ủ": 89,
"ứ": 79,
"ừ": 70,
"ử": 13,
"ữ": 102,
"ự": 105,
"ỳ": 31,
"ỷ": 94,
"ỹ": 35
}