add tokenizer

vocab.json

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