add tokenizer

vocab.json

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