add tokenizer

vocab.json

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