add tokenizer

vocab.json

@@ -1 +1 @@
-{"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}
+{"ن": 0, "ا": 1, "ٌ": 2, "ل": 3, "ي": 4, "ؤ": 5, "ض": 6, "ص": 7, "ٍ": 8, "إ": 9, "ً": 10, "ی": 11, "أ": 12, "ة": 13, "ف": 14, "ذ": 15, "َ": 16, "غ": 17, "؟": 18, "ٰ": 19, "ج": 20, "ۖ": 21, "ش": 22, "،": 23, "آ": 24, "س": 25, "ث": 26, "ه": 27, "ى": 28, "ح": 29, "ك": 30, "ع": 31, "ّ": 32, "ْ": 33, "ئ": 34, "ت": 35, "ب": 36, "ر": 37, "ُ": 38, "ط": 39, "ز": 40, "ظ": 41, "د": 42, "م": 44, "ق": 45, "ـ": 46, "ء": 47, "ِ": 48, "و": 49, "خ": 50, "|": 43, "[UNK]": 51, "[PAD]": 52}