add tokenizer

vocab.json

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