add tokenizer

vocab.json

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