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, "ٓ": 30, "ٹ": 31, "پ": 32, "چ": 33, "ڈ": 34, "ڑ": 35, "ژ": 36, "ک": 37, "گ": 38, "ں": 39, "ھ": 40, "ہ": 41, "ی": 42, "ے": 43, "’": 44, "|": 0, "<unk>": 45, "<pad>": 46, "<s>": 47, "</s>": 48}
+{"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, "ٹ": 29, "پ": 30, "چ": 31, "ڈ": 32, "ڑ": 33, "ژ": 34, "ک": 35, "گ": 36, "ں": 37, "ھ": 38, "ہ": 39, "ی": 40, "ے": 41, "|": 0, "<unk>": 42, "<pad>": 43, "<s>": 44, "</s>": 45}