add tokenizer

vocab.json

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