add tokenizer

vocab.json

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