add tokenizer

vocab.json

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