add tokenizer

vocab.json

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