Open 100tomer opened 1 year ago
Hi @100tomer,
Currently, whisper kernel does not support the GPU acceleration library for Apple, which is far beyond my capabilities. However, I have learned that there is a project underway to address this issue.
As an alternative solution, I will release a light-weight version(#19) that will achieve satisfactory results by compressed audio and through OpenAI API integration. This should be completed in the near future and included in version 3.1.
Hi @100tomer,
Currently, whisper kernel does not support the GPU acceleration library for Apple, which is far beyond my capabilities.
However, I have learned that there is a project underway to address this issue.
As an alternative solution, I will release a light-weight version(#19) that will achieve satisfactory results by compressed audio and through OpenAI API integration.
This should be completed in the near future and included in version 3.1.
Thanks, sounds great
it is actually not faster with GPU. there is a cpp version of Whisper which is also on GitHub. The author tested the GPU vs CPU and found it is close in terms of performence . his guess was the bandwidth is the limitation.
it is actually not faster with GPU. there is a cpp version of Whisper which is also on GitHub. The author tested the GPU vs CPU and found it is close in terms of performence . his guess was the bandwidth is the limitation.
Oh that's the ram bandwidth? Or the SSD bandwidth? Also does it use GPU only or the Neural Engine too?
I don't know if it's even possible, but it would be cool and efficient to have it run on M1/2 with GPU or Neural Engine