add tokenizer

vocab.json

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