add tokenizer

vocab.json

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