add tokenizer

vocab.json

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