add tokenizer

vocab.json

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