add tokenizer

vocab.json

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