add tokenizer

vocab.json

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