add tokenizer

vocab.json

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