add tokenizer

vocab.json

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