add tokenizer

vocab.json

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