add tokenizer

vocab.json

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