add tokenizer

vocab.json

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