add tokenizer

vocab.json

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