add tokenizer

vocab.json

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