add tokenizer

vocab.json

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