add tokenizer

vocab.json

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