add tokenizer

vocab.json

@@ -1 +1 @@
-{"d": 0, "s": 1, "t": 2, "v": 3, "e": 4, "u": 5, "y": 6, "h": 7, "i": 8, "o": 9, "c": 10, "m": 12, "z": 13, "b": 14, "r": 15, "j": 16, "q": 17, "x": 18, "a": 19, "p": 20, "l": 21, "k": 22, "g": 23, "'": 24, "w": 25, "n": 26, "f": 27, "|": 11, "[UNK]": 28, "[PAD]": 29}
+{"n": 0, "c": 1, "t": 2, "b": 3, "v": 4, "u": 5, "'": 6, "o": 7, "d": 8, "f": 9, "y": 11, "m": 12, "l": 13, "s": 14, "x": 15, "q": 16, "e": 17, "w": 18, "h": 19, "k": 20, "r": 21, "a": 22, "j": 23, "z": 24, "p": 25, "g": 26, "i": 27, "|": 10, "[UNK]": 28, "[PAD]": 29}