add tokenizer

vocab.json

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