add tokenizer

vocab.json

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