wav2vec2-vi / vocab.json
qbaro's picture
add tokenizer
dba62a2
{"(": 1, ")": 2, "*": 3, "0": 4, "1": 5, "2": 6, "3": 7, "4": 8, "5": 9, "7": 10, "8": 11, "9": 12, "\\": 13, "a": 14, "b": 15, "c": 16, "d": 17, "e": 18, "f": 19, "g": 20, "h": 21, "i": 22, "j": 23, "k": 24, "l": 25, "m": 26, "n": 27, "o": 28, "p": 29, "q": 30, "r": 31, "s": 32, "t": 33, "u": 34, "v": 35, "w": 36, "x": 37, "y": 38, "z": 39, "à": 40, "á": 41, "ã": 42, "è": 43, "é": 44, "ê": 45, "ì": 46, "í": 47, "ð": 48, "ò": 49, "ó": 50, "õ": 51, "ù": 52, "ú": 53, "ý": 54, "ă": 55, "đ": 56, "ĩ": 57, "ũ": 58, "ơ": 59, "ư": 60, "̀": 61, "́": 62, "̃": 63, "̣": 64, "ạ": 65, "ả": 66, "ấ": 67, "ầ": 68, "ẩ": 69, "ẫ": 70, "ậ": 71, "ắ": 72, "ằ": 73, "ẳ": 74, "ẵ": 75, "ặ": 76, "ẹ": 77, "ẻ": 78, "ẽ": 79, "ế": 80, "ề": 81, "ể": 82, "ễ": 83, "ệ": 84, "ỉ": 85, "ị": 86, "ọ": 87, "ỏ": 88, "ố": 89, "ồ": 90, "ổ": 91, "ỗ": 92, "ộ": 93, "ớ": 94, "ờ": 95, "ở": 96, "ỡ": 97, "ợ": 98, "ụ": 99, "ủ": 100, "ứ": 101, "ừ": 102, "ử": 103, "ữ": 104, "ự": 105, "ỳ": 106, "ỵ": 107, "ỷ": 108, "ỹ": 109, "’": 110, "…": 111, "|": 0, "[UNK]": 112, "[PAD]": 113}