add tokenizer

vocab.json

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