add tokenizer

vocab.json

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