add tokenizer

vocab.json

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