add tokenizer

vocab.json

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