add tokenizer

vocab.json

@@ -1 +1 @@
-{"ل": 0, "غ": 1, "ش": 2, "ح": 3, "د": 4, "ہ": 5, "ف": 6, "آ": 8, "ٹ": 9, "ڈ": 10, "م": 11, "ی": 12, "ا": 13, "ھ": 14, "ے": 15, "ت": 16, "ں": 17, "پ": 18, "ق": 19, "گ": 20, "ر": 21, "و": 22, "ک": 23, "ن": 24, "س": 25, "|": 7, "[UNK]": 26, "[PAD]": 27}
+{"س": 0, "پ": 1, "ح": 2, "ق": 3, "د": 4, "ر": 5, "غ": 6, "و": 7, "ف": 8, "ش": 9, "ھ": 10, "ڈ": 11, "ٹ": 12, "ا": 13, "آ": 14, "ے": 15, "ک": 16, "ں": 17, "ی": 18, "ل": 19, "گ": 20, "ت": 21, "ن": 22, "م": 23, "ہ": 24, "|": 25, "[UNK]": 26, "[PAD]": 27}