add tokenizer

vocab.json

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