add tokenizer

vocab.json

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