add tokenizer

vocab.json

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