add tokenizer

vocab.json

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