On Mon, Mar 4, 2019 at 5:53 PM Adrian Musceac <kanto...@gmail.com> wrote: > How does this scale for normal hams though? Do each of us need a huge > GPU and voice samples to even be able to use this? I am afraid that > this might have even less success with hams than current FreeDV > releases.
The trained network is part of the codec just as a table of constants. The end user doesn't need a GPU. To do development of the codec itself you'll probably need a GPU. There are many rather large collections of speech samples that can be used for training. _______________________________________________ Freetel-codec2 mailing list Freetel-codec2@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/freetel-codec2
