add tokenizer

vocab.json

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