add tokenizer

vocab.json

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