add tokenizer

vocab.json

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