add tokenizer

vocab.json

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