add tokenizer

vocab.json

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