Wiam's picture
add tokenizer
47580f3
raw history blame
No virus
485 Bytes
{"أ": 0, "ب": 1, "ظ": 2, "ث": 3, "ذ": 4, "؟": 5, "ي": 6, "ّ": 7, "ئ": 8, "،": 9, "ل": 10, "ز": 11, "ة": 12, "ح": 13, "ع": 14, "ض": 15, "ج": 16, "ن": 17, "َ": 18, "ق": 19, "ش": 20, "ص": 21, "ه": 22, "ر": 23, "إ": 24, "د": 25, "ت": 26, "خ": 27, "ً": 29, "ك": 30, "ؤ": 31, "م": 32, "ِ": 33, "ٍ": 34, "ء": 35, "ٌ": 36, "و": 37, "س": 38, "ُ": 39, "آ": 40, "ا": 41, "ط": 42, "ى": 43, "ف": 44, "ْ": 45, "غ": 46, "|": 28, "[UNK]": 47, "[PAD]": 48}