add tokenizer

vocab.json

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