add tokenizer

vocab.json

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