chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 10:07:28 -04:00
Code Issues Packages Projects Releases Wiki Activity

Revert "docs: add troubleshooting section for libcudnn dependencies in README"

Browse Source 
This reverts commit 6fe0a8784a.

Revert the commit now that the issue is fixed.

Signed-off-by: CHEN, CHUN <jim60105@gmail.com>
This commit is contained in:
CHEN, CHUN
2025-06-14 00:22:05 +08:00
parent d3dcb1175f
commit 399010fd12
1 changed files with 0 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@ -97,25 +97,6 @@ uv sync --all-extras --dev
You may also need to install ffmpeg, rust etc. Follow openAI instructions here https://github.com/openai/whisper#setup.
### Common Issues & Troubleshooting 🔧
#### libcudnn Dependencies (GPU Users)
If you're using WhisperX with GPU support and encounter errors like:
- `Could not load library libcudnn_ops_infer.so.8`
- `Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}`
- `libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory`
This means your system is missing the CUDA Deep Neural Network library (cuDNN). This library is needed for GPU acceleration but isn't always installed by default.
**Install cuDNN (example for apt based systems):**
```bash
sudo apt update
sudo apt install libcudnn8 libcudnn8-dev -y
```
### Speaker Diarization
To **enable Speaker Diarization**, include your Hugging Face access token (read) that you can generate from [Here](https://huggingface.co/settings/tokens) after the `--hf_token` argument and accept the user agreement for the following models: [Segmentation](https://huggingface.co/pyannote/segmentation-3.0) and [Speaker-Diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) (if you choose to use Speaker-Diarization 2.x, follow requirements [here](https://huggingface.co/pyannote/speaker-diarization) instead.)