add tokenizer

vocab.json

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