add tokenizer

vocab.json

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