add tokenizer

vocab.json

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