add tokenizer

vocab.json

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