About the sprakbanken corpus:
This corpus is a free corpus originally collected by NST for ASR purposes and currently hosted by the Norwegian libraries. The corpus is multilingual and contains Swedish, Norwegian (Bokmål) and Danish. This setup uses the Swedish subcorpus and it is created by me, Emelie Kullmann, from the original Sprakbanken-recipe which uses the Danish subcorpus. The vocabulary is large and there is approx. 480 hours of read-aloud speech with associated text scripts.
Some months ago the corpus was republished here: http://www.nb.no/sprakbanken/#ticketsfrom?lang=en
s5: This is the current recommended recipe. (Swedish)