add tokenizer

vocab.json

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