add tokenizer

vocab.json

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