add tokenizer

vocab.json

@@ -1 +1 @@
-{"d": 0, "m": 1, "l": 2, "t": 3, "b": 4, "q": 5, "a": 6, "o": 7, "p": 8, "k": 9, "f": 10, "y": 11, "x": 12, "s": 13, "z": 14, "u": 15, "'": 16, "v": 17, "h": 18, "j": 20, "n": 21, "g": 22, "r": 23, "e": 24, "i": 25, "c": 26, "w": 27, "|": 19, "[UNK]": 28, "[PAD]": 29}
+{"\"": 0, "f": 1, "r": 2, "k": 3, ":": 4, "g": 5, "m": 6, "n": 7, "-": 8, "l": 9, "v": 10, "'": 11, "z": 12, "u": 13, ".": 14, "b": 15, "c": 16, "q": 17, "s": 18, "?": 19, "j": 21, "h": 22, ";": 23, "o": 24, "i": 25, "a": 26, "p": 27, "t": 28, "x": 29, "d": 30, ",": 31, "e": 32, "y": 33, "!": 34, "w": 35, "|": 20, "[UNK]": 36, "[PAD]": 37}