add tokenizer

vocab.json

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