add tokenizer

vocab.json

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