add tokenizer

vocab.json

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