add tokenizer

vocab.json

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