LI TIANCHENG
LI TIANCHENG
> @OutisLi The TestFlight demo app should work without an internet connection after the first model download. Could you share more details on how the problem manifests? Since I need...
目前pytorch的windows版本不支持50系，fastwhisper添加--compute_type float16后可以运行，但是好像还是有问题，可以等我的whisper.cpp合并后使用whispercpp。
Do not need this. For translation purpose, normal LLM is enough. Thinking model is slow and expensive
This PR #104 solved this
> @OutisLi Are you on an M1 device by any chance? `*turbo*` models are incompatible with M1 devices but you can still generate non-turbo models with `--audio-encoder-sdpa-implementation Cat` while executing...
LCAO perhaps？Thanks a lot On Tue, Apr 1, 2025 at 20:27 Mohan Chen ***@***.***> wrote: > Do you want results for PW basis or LCAO basis? > > — >...
> [@OutisLi](https://github.com/OutisLi) Do you think the answer is sufficient? Thanks a lot. I tested the demo and my result is shown below: PC 1: AMD 7950X3D with 24G RAM +...
Besides, I install abacus through conda, my installation commands for intel+nvidia and amd+nvidia are as shown below respectively: #### INTEL + NVIDIA ```shell conda update -n base -c defaults conda...
the name is so confussing
> To get this to work I had to do: > > ``` > pip install "numpy