global_processor / vocab.json
ilyes25's picture
Upload processor
f2d6697 verified
{
"!": 0,
"#": 1,
"$": 2,
"&": 3,
"'": 4,
"*": 5,
"+": 6,
"-": 7,
"/": 8,
"0": 9,
"1": 10,
"2": 11,
"3": 12,
"4": 13,
"5": 14,
"6": 15,
"7": 16,
"8": 17,
"9": 18,
"</s>": 19,
"<ar>": 20,
"<dz>": 21,
"<fr>": 22,
"<kab>": 23,
"<s>": 24,
"=": 25,
"?": 26,
"[": 27,
"[PAD]": 28,
"[UNK]": 29,
"]": 30,
"a": 31,
"b": 32,
"c": 33,
"d": 34,
"e": 35,
"f": 36,
"g": 37,
"h": 38,
"i": 39,
"j": 40,
"k": 41,
"l": 42,
"m": 43,
"n": 44,
"o": 45,
"p": 46,
"q": 47,
"r": 48,
"s": 49,
"t": 50,
"u": 51,
"v": 52,
"w": 53,
"x": 54,
"y": 55,
"z": 56,
"|": 57,
"~": 58,
"°": 59,
"²": 60,
"´": 61,
"·": 62,
"à": 63,
"á": 64,
"â": 65,
"ã": 66,
"ä": 67,
"ç": 68,
"è": 69,
"é": 70,
"ê": 71,
"ë": 72,
"ì": 73,
"í": 74,
"î": 75,
"ï": 76,
"ð": 77,
"ñ": 78,
"ò": 79,
"ó": 80,
"ô": 81,
"õ": 82,
"ö": 83,
"ù": 84,
"ú": 85,
"û": 86,
"ü": 87,
"ā": 88,
"ă": 89,
"č": 90,
"ē": 91,
"ĕ": 92,
"ė": 93,
"ī": 94,
"ĭ": 95,
"ń": 96,
"ō": 97,
"ŏ": 98,
"ő": 99,
"œ": 100,
"ş": 101,
"š": 102,
"ţ": 103,
"ũ": 104,
"ū": 105,
"ų": 106,
"ƙ": 107,
"ƴ": 108,
"ǃ": 109,
"ǧ": 110,
"ǹ": 111,
"ɓ": 112,
"ɔ": 113,
"ɖ": 114,
"ɗ": 115,
"ɛ": 116,
"ɣ": 117,
"ɨ": 118,
"ʻ": 119,
"ː": 120,
"̀": 121,
"́": 122,
"̄": 123,
"̆": 124,
"̇": 125,
"̜": 126,
"̣": 127,
"̧": 128,
"̻": 129,
"̼": 130,
"͕": 131,
"γ": 132,
"ε": 133,
"μ": 134,
"σ": 135,
"ԑ": 136,
"ء": 137,
"آ": 138,
"أ": 139,
"ؤ": 140,
"إ": 141,
"ئ": 142,
"ا": 143,
"ب": 144,
"ة": 145,
"ت": 146,
"ث": 147,
"ج": 148,
"ح": 149,
"خ": 150,
"د": 151,
"ذ": 152,
"ر": 153,
"ز": 154,
"س": 155,
"ش": 156,
"ص": 157,
"ض": 158,
"ط": 159,
"ظ": 160,
"ع": 161,
"غ": 162,
"ـ": 163,
"ف": 164,
"ق": 165,
"ك": 166,
"ل": 167,
"م": 168,
"ن": 169,
"ه": 170,
"و": 171,
"ى": 172,
"ي": 173,
"ً": 174,
"ٌ": 175,
"ٍ": 176,
"َ": 177,
"ُ": 178,
"ِ": 179,
"ّ": 180,
"ْ": 181,
"่": 182,
"ḅ": 183,
"ḍ": 184,
"ḥ": 185,
"ḿ": 186,
"ṅ": 187,
"ṛ": 188,
"ṣ": 189,
"ṭ": 190,
"ẓ": 191,
"ạ": 192,
"ẹ": 193,
"ẽ": 194,
"ị": 195,
"ọ": 196,
"ụ": 197,
"–": 198,
"’": 199,
"…": 200,
"₂": 201,
"₦": 202,
"€": 203
}