wav2vec2-base-asr-2 / vocab.json
LanPham's picture
add tokenizer
46c8c1f
{"ị": 0, "đ": 1, "ó": 2, "ỉ": 3, "ứ": 4, "ự": 5, "c": 6, "ỷ": 7, "ă": 8, "ấ": 9, "ờ": 10, "ẫ": 11, "y": 12, "n": 13, "ẩ": 14, "ẹ": 15, "ạ": 16, "ẻ": 17, "ũ": 18, "ù": 19, "d": 20, "e": 21, "ồ": 22, "ề": 23, "ỗ": 24, "á": 25, "ể": 26, "ỹ": 27, "ô": 28, "a": 29, "ơ": 30, "ý": 31, "ổ": 32, "ầ": 33, "x": 34, "ê": 35, "ú": 36, "r": 38, "u": 39, "s": 40, "b": 41, "õ": 42, "ỳ": 43, "o": 44, "ữ": 45, "ụ": 46, "i": 47, "ệ": 48, "ễ": 49, "ỏ": 50, "ỡ": 51, "ẵ": 52, "ủ": 53, "à": 54, "l": 55, "â": 56, "ộ": 57, "ế": 58, "è": 59, "ư": 60, "ặ": 61, "ọ": 62, "ò": 63, "ử": 64, "m": 65, "ớ": 66, "ợ": 67, "ậ": 68, "ắ": 69, "g": 70, "v": 71, "ừ": 72, "ã": 73, "í": 74, "q": 75, "ở": 76, "ả": 77, "t": 78, "ằ": 79, "ố": 80, "ẽ": 81, "k": 82, "h": 83, "ì": 84, "p": 85, "é": 86, "ĩ": 87, "|": 37, "[UNK]": 88, "[PAD]": 89}