add tokenizer

vocab.json

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