add tokenizer

vocab.json

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