add tokenizer

vocab.json

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