add tokenizer

vocab.json

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