Anyone know of any good blogs or discussion sites for finding and sharing #lightweight #software? I've mentioned a few resources here: https://lmemsm.dreamwidth.org/1142.html
Would be interested in finding others. Recommendations appreciated. Thanks.
@alcinnz Rhapsode looks like a very interesting project. Really like the accessibility aspects. I did some porting of netrider at one point: https://sourceforge.net/projects/netrider/ What do think of CMU Sphinx for speech recognition? Was looking at it and Kaldi. Sphinx is much easier to build from source than Kaldi. Good luck with your project. Seems really nice.
@lmemsm Thanks. CMU Sphinx is working very well for me!
(Yup, my homepage is updated to say I'm using Voice2JSON, which can alternatively wrap Kaldi, DeepSpeech, or Julius)
@lmemsm Judging by the code from these different speech recognitions engines, I would expect Kaldi to be more accurate than PocketSphinx. Architecturally the two are roughly equivalent, but Kaldi is much more featureful.
DeepSpeech & Julius meanwhile are more opinionated about how they work, should improve reliability. Though neuralnets don't look as appropriate for my use, they're harder to guide towards valid responses.
Most of the projects on there are written in assembly for Uxn, but I recommend trying Dotgrid and Moogle :)
Scholar Social is a microblogging platform for researchers, grad students, librarians, archivists, undergrads, academically inclined high schoolers, educators of all levels, journal editors, research assistants, professors, administrators—anyone involved in academia who is willing to engage with others respectfully.