add tokenizer

vocab.json

@@ -1 +1 @@
-{"$": 0, "a": 1, "h": 2, "c": 3, "r": 4, "s": 5, "z": 6, "x": 7, "n": 8, "v": 9, "k": 10, "u": 12, "d": 13, "l": 14, "o": 15, "g": 16, "i": 17, "b": 18, "f": 19, "w": 20, "j": 21, "m": 22, "t": 23, "y": 24, "q": 25, "'": 26, "p": 27, "e": 28, "|": 11, "[UNK]": 29, "[PAD]": 30}
+{"d": 1, "x": 2, "s": 3, "l": 4, "f": 5, "e": 6, "o": 7, "p": 8, "u": 9, "k": 10, "r": 11, "j": 12, "'": 13, "t": 14, "q": 15, "w": 16, "y": 17, "b": 18, "v": 19, "z": 20, "m": 21, "i": 22, "a": 23, "n": 24, "$": 25, "g": 26, "c": 27, "h": 28, "|": 0, "[UNK]": 29, "[PAD]": 30}