add tokenizer

vocab.json

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