add tokenizer

vocab.json

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