add tokenizer

vocab.json

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