| { | |
| "\n": 0, | |
| "!": 2, | |
| "\"": 3, | |
| "#": 4, | |
| "%": 5, | |
| "&": 6, | |
| "'": 7, | |
| "(": 8, | |
| ")": 9, | |
| "*": 10, | |
| "+": 11, | |
| ",": 12, | |
| "-": 13, | |
| ".": 14, | |
| "/": 15, | |
| "0": 16, | |
| "1": 17, | |
| "2": 18, | |
| "3": 19, | |
| "4": 20, | |
| "5": 21, | |
| "6": 22, | |
| "7": 23, | |
| "8": 24, | |
| "9": 25, | |
| ":": 26, | |
| "=": 27, | |
| "?": 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, | |
| "[": 55, | |
| "[PAD]": 174, | |
| "[UNK]": 173, | |
| "\\": 56, | |
| "]": 57, | |
| "_": 58, | |
| "a": 59, | |
| "b": 60, | |
| "c": 61, | |
| "d": 62, | |
| "e": 63, | |
| "f": 64, | |
| "g": 65, | |
| "h": 66, | |
| "i": 67, | |
| "j": 68, | |
| "k": 69, | |
| "l": 70, | |
| "m": 71, | |
| "n": 72, | |
| "o": 73, | |
| "p": 74, | |
| "q": 75, | |
| "r": 76, | |
| "s": 77, | |
| "t": 78, | |
| "u": 79, | |
| "v": 80, | |
| "w": 81, | |
| "x": 82, | |
| "y": 83, | |
| "z": 84, | |
| "|": 1, | |
| " ": 85, | |
| "«": 86, | |
| "»": 87, | |
| "ç": 88, | |
| "è": 89, | |
| "é": 90, | |
| "í": 91, | |
| "ö": 92, | |
| "ā": 93, | |
| "ō": 94, | |
| "ǎ": 95, | |
| "ǒ": 96, | |
| "،": 97, | |
| "؛": 98, | |
| "؟": 99, | |
| "ء": 100, | |
| "آ": 101, | |
| "أ": 102, | |
| "ؤ": 103, | |
| "إ": 104, | |
| "ئ": 105, | |
| "ا": 106, | |
| "ب": 107, | |
| "ة": 108, | |
| "ت": 109, | |
| "ث": 110, | |
| "ج": 111, | |
| "ح": 112, | |
| "خ": 113, | |
| "د": 114, | |
| "ذ": 115, | |
| "ر": 116, | |
| "ز": 117, | |
| "س": 118, | |
| "ش": 119, | |
| "ص": 120, | |
| "ض": 121, | |
| "ط": 122, | |
| "ظ": 123, | |
| "ع": 124, | |
| "غ": 125, | |
| "ـ": 126, | |
| "ف": 127, | |
| "ق": 128, | |
| "ك": 129, | |
| "ل": 130, | |
| "م": 131, | |
| "ن": 132, | |
| "ه": 133, | |
| "و": 134, | |
| "ى": 135, | |
| "ي": 136, | |
| "ً": 137, | |
| "ٌ": 138, | |
| "ٍ": 139, | |
| "َ": 140, | |
| "ُ": 141, | |
| "ِ": 142, | |
| "ّ": 143, | |
| "ْ": 144, | |
| "ٓ": 145, | |
| "ٗ": 146, | |
| "٠": 147, | |
| "١": 148, | |
| "٢": 149, | |
| "٣": 150, | |
| "٧": 151, | |
| "٨": 152, | |
| "٩": 153, | |
| "٫": 154, | |
| "ٰ": 155, | |
| "ٱ": 156, | |
| "پ": 157, | |
| "چ": 158, | |
| "ڢ": 159, | |
| "ڤ": 160, | |
| "ڨ": 161, | |
| "ی": 162, | |
| "ۡ": 163, | |
| "": 164, | |
| "—": 165, | |
| "‘": 166, | |
| "’": 167, | |
| "…": 168, | |
| "": 169, | |
| "ﻷ": 170, | |
| "ﻻ": 171, | |
| "": 172 | |
| } | |