Related, does it handle whitenoise (ie not talking) well? I'd be interested in running this over a home camera system, but it would need to handle not talking well. Also movies and music might cause issues, too.
It can do faster than real time
Real time means it doesn't need the whole audio clip to work..
I guess "streaming" would be a suitable expression in that case.
thank you! yes streaming is the right terminology here
I think there is more to it than just batch speed. For real-time processing you can’t look ahead Beyond the current buffer. Basically the question is can the model be run in a streaming fashion, and is it still fast running that way