add tokenizer

vocab.json

@@ -1 +1 @@
-{"c": 0, "q": 1, "o": 2, "m": 3, "a": 4, "u": 5, "r": 6, "s": 7, "w": 8, "h": 9, "b": 10, "z": 11, "y": 13, "j": 14, "k": 16, "f": 17, "t": 18, "i": 19, "e": 20, "d": 21, "l": 22, "g": 23, "v": 24, "x": 25, "p": 26, "n": 27, "[UNK]": 28, "[PAD]": 29, "|": 12}
+{"n": 0, "s": 1, "h": 2, "j": 3, "m": 4, "e": 5, "y": 6, "o": 7, "i": 8, "g": 9, "d": 10, "b": 11, "v": 12, "u": 13, "t": 14, "w": 15, "k": 16, "l": 17, "c": 18, "p": 19, "f": 20, "q": 21, "x": 22, "a": 23, "r": 26, "z": 27, "[UNK]": 28, "[PAD]": 29, "|": 24}