add tokenizer

vocab.json

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