add tokenizer

vocab.json

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