add tokenizer

vocab.json

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