add tokenizer

vocab.json

@@ -1 +1 @@
-{"p": 0, "o": 1, "i": 2, "m": 4, "t": 5, "r": 6, "w": 7, "u": 8, "ä": 9, "b": 10, "a": 11, "x": 12, "ö": 13, "h": 14, "y": 15, "å": 16, "g": 17, "n": 18, "v": 19, "e": 20, "z": 30, "d": 22, "j": 23, "c": 24, "k": 25, "s": 26, "l": 27, "q": 28, "f": 29, "|": 3, "[UNK]": 30, "[PAD]": 31}
+{"r": 0, "s": 1, "t": 2, "å": 3, "k": 5, "e": 6, "y": 7, "z": 30, "o": 9, "q": 10, "c": 11, "b": 12, "j": 13, "m": 14, "a": 15, "v": 16, "n": 17, "ö": 18, "g": 19, "h": 20, "x": 21, "p": 22, "i": 23, "w": 24, "f": 25, "ä": 26, "l": 27, "d": 28, "u": 29, "|": 4, "[UNK]": 30, "[PAD]": 31}