add tokenizer

vocab.json

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