add tokenizer

vocab.json

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