add tokenizer

vocab.json

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