add tokenizer

vocab.json

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