add tokenizer

vocab.json

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