add tokenizer

vocab.json

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