Now you have my interest, because usually whenever the terms "hardware acceleration" are mentioned, it's usually yet another software jumping into the CUDA bandwagon because of supposed widespread support or because nVidia decided it wants to care about that particular piece of software because of rea$ons. And I also had some crash with DirectML on some AI models, so let see what will be the situation in a couple months. I added "where possible" because I know some hardware accelerator such as CoreML can't support all kind of AI nodes, so all AIs may not benefit from CoreML acceleration. Hopefully the situation will be better in a couple months. I've already done some tests with those accelerators, but did not judge them stable enough for the launch date. Concerning future hardware acceleration, it'll likely be based on DirectML (on Windows) which allows support for NVIDIA, AMD and Intel HD Graphics GPUs, and on CoreML on macOS. Here's a screenshot of a song unmixed in SL10. You were wondering about frequencies above 17k. 15sec on SL10 in Fast mode (which is much higher quality than SL9) On a macbook air M1, using CPU to unmix 45sec of stereo audio it takes: The improved Hybrid Transformer Demucs implementation in SL10 is pretty fast - actually faster than the Spleeter implementation in previous versions of SL. Hi de Souza Lino, SpectraLayers developer here - to answer your questions:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |