add tokenizer

vocab.json

@@ -1 +1 @@
-{"n": 0, "a": 1, "b": 2, "t": 3, "q": 4, "p": 5, "l": 6, "x": 7, "r": 9, "m": 10, "g": 11, "c": 12, "d": 13, "f": 14, "u": 15, "h": 17, "z": 18, "o": 19, "v": 20, "k": 21, "w": 22, "'": 23, "s": 24, "y": 25, "i": 26, "e": 27, "j": 28, "|": 24, "[UNK]": 28, "[PAD]": 29}
+{"o": 0, "v": 1, "s": 2, "b": 3, "d": 4, "y": 5, "a": 6, "h": 7, "q": 8, "x": 9, "m": 10, "j": 11, "r": 12, "c": 14, "'": 15, "e": 16, "k": 17, "w": 18, "t": 20, "g": 21, "f": 22, "i": 23, "u": 24, "p": 25, "z": 26, "l": 27, "n": 28, "|": 32, "[UNK]": 28, "[PAD]": 29}