Very nice! Especially that it can run with good speed on the CPU without any external dependencies.
I wish something like this would also exist for Stable Diffusion - a simple, no dependency way to run it with C++ on the CPU with AVX. Do you know if that would be possible with your tensor library, or is it very hardcoded for Whisper?
I wish something like this would also exist for Stable Diffusion - a simple, no dependency way to run it with C++ on the CPU with AVX. Do you know if that would be possible with your tensor library, or is it very hardcoded for Whisper?