add tokenizer

vocab.json

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