add tokenizer

vocab.json

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