add tokenizer

vocab.json

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