add tokenizer

vocab.json

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