add tokenizer

vocab.json

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