add tokenizer

vocab.json

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