add tokenizer

vocab.json

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