add tokenizer

vocab.json

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