add tokenizer

vocab.json

@@ -1 +1 @@
-{"a": 0, "i": 2, "o": 3, "y": 4, "t": 5, "q": 6, "p": 7, "m": 8, "b": 9, "c": 10, "f": 11, "n": 12, "u": 13, "g": 14, "k": 15, "j": 17, "s": 18, "r": 19, "h": 20, "d": 21, "e": 22, "w": 23, "z": 24, "v": 25, "x": 26, "l": 27, "[UNK]": 28, "[PAD]": 29, "|": 16}
+{"y": 0, "w": 2, "v": 3, "c": 4, "t": 6, "f": 7, "d": 8, "s": 9, "l": 10, "b": 11, "r": 12, "n": 13, "z": 14, "m": 15, "k": 16, "x": 17, "e": 18, "u": 19, "q": 20, "o": 21, "j": 22, "h": 23, "g": 24, "p": 25, "a": 26, "i": 27, "[UNK]": 28, "[PAD]": 29, "|": 5}