add tokenizer

vocab.json

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