add tokenizer

vocab.json

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