{ | |
"!": 1, | |
"\"": 2, | |
"%": 3, | |
"&": 4, | |
"'": 5, | |
"*": 6, | |
"+": 7, | |
",": 8, | |
"-": 9, | |
".": 10, | |
"/": 11, | |
"0": 12, | |
"1": 13, | |
"2": 14, | |
"3": 15, | |
"4": 16, | |
"5": 17, | |
"6": 18, | |
"7": 19, | |
"8": 20, | |
"9": 21, | |
":": 22, | |
"<": 23, | |
"=": 24, | |
">": 25, | |
"?": 26, | |
"[": 27, | |
"[PAD]": 123, | |
"[UNK]": 122, | |
"]": 28, | |
"a": 29, | |
"b": 30, | |
"c": 31, | |
"d": 32, | |
"e": 33, | |
"f": 34, | |
"g": 35, | |
"h": 36, | |
"i": 37, | |
"j": 38, | |
"k": 39, | |
"l": 40, | |
"m": 41, | |
"n": 42, | |
"o": 43, | |
"p": 44, | |
"q": 45, | |
"r": 46, | |
"s": 47, | |
"t": 48, | |
"u": 49, | |
"v": 50, | |
"w": 51, | |
"x": 52, | |
"y": 53, | |
"z": 54, | |
"|": 0, | |
"à": 56, | |
"á": 57, | |
"â": 58, | |
"ã": 59, | |
"è": 60, | |
"é": 61, | |
"ê": 62, | |
"ì": 63, | |
"í": 64, | |
"ò": 65, | |
"ó": 66, | |
"ô": 67, | |
"õ": 68, | |
"ù": 69, | |
"ú": 70, | |
"ý": 71, | |
"ă": 72, | |
"đ": 73, | |
"ĩ": 74, | |
"ũ": 75, | |
"ơ": 76, | |
"ư": 77, | |
"ạ": 78, | |
"ả": 79, | |
"ấ": 80, | |
"ầ": 81, | |
"ẩ": 82, | |
"ẫ": 83, | |
"ậ": 84, | |
"ắ": 85, | |
"ằ": 86, | |
"ẳ": 87, | |
"ẵ": 88, | |
"ặ": 89, | |
"ẹ": 90, | |
"ẻ": 91, | |
"ẽ": 92, | |
"ế": 93, | |
"ề": 94, | |
"ể": 95, | |
"ễ": 96, | |
"ệ": 97, | |
"ỉ": 98, | |
"ị": 99, | |
"ọ": 100, | |
"ỏ": 101, | |
"ố": 102, | |
"ồ": 103, | |
"ổ": 104, | |
"ỗ": 105, | |
"ộ": 106, | |
"ớ": 107, | |
"ờ": 108, | |
"ở": 109, | |
"ỡ": 110, | |
"ợ": 111, | |
"ụ": 112, | |
"ủ": 113, | |
"ứ": 114, | |
"ừ": 115, | |
"ử": 116, | |
"ữ": 117, | |
"ự": 118, | |
"ỳ": 119, | |
"ỷ": 120, | |
"ỹ": 121, | |
"₫": 122 | |
} | |