deblan-mirror/buzz
1
0
Fork 0
mirror of https://github.com/chidiwilliams/buzz.git synced 2026-03-14 22:55:46 +01:00
Code Issues Projects Releases Packages Wiki Activity

Add documantation (#872)

Browse source
This commit is contained in:
Raivis Dejus 2024-08-04 19:31:52 +03:00 • committed by GitHub
commit 38e1254adf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 6 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
CONTRIBUTING.md
View file

@ -54,6 +54,11 @@ On versions prior to Ubuntu 24.04 install `sudo apt-get install --no-install-rec
7. Build Buzz `poetry build`
8. Run Buzz `python -m buzz`
#### Necessary dependencies for Faster Whisper on GPU
All the dependencies for GPU support should be included in the dependency packages already installed,
but if you get issues running Faster Whisper on GPU, install [CUDA 12](https://developer.nvidia.com/cuda-downloads), [cuBLASS](https://developer.nvidia.com/cublas) and [cuDNN](https://developer.nvidia.com/cudnn).
#### Error for Faster Whisper on GPU `Could not load library libcudnn_ops_infer.so.8`
You need to add path to the library to the `LD_LIBRARY_PATH` environment variable.

2
docs/docs/faq.md
View file

@ -31,6 +31,6 @@ sidebar_position: 5
4. **How to get GPU acceleration for faster transcription?**
On Linux GPU acceleration is supported out of the box on Nvidia GPUs with [CUDA installed](https://developer.nvidia.com/cuda-downloads).
On Linux GPU acceleration is supported out of the box on Nvidia GPUs. If you still get any issues install [CUDA 12](https://developer.nvidia.com/cuda-downloads), [cuBLASS](https://developer.nvidia.com/cublas) and [cuDNN](https://developer.nvidia.com/cudnn).
On Windows see [this note](https://github.com/chidiwilliams/buzz/blob/main/CONTRIBUTING.md#gpu-support) on enabling CUDA GPU support.