add tokenizer

vocab.json

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