admin/LC_NeoRefacer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Supress CUDA path error in CPU mode

Browse Source
This commit is contained in:
Felipe Daragon
2025-04-16 21:14:48 +01:00
parent baf66f8570
commit 99c91d20b2
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -77,7 +77,7 @@ On Windows, before continuing, ensure that you have the [Visual Studio Build Too
Follow these steps to install Refacer and its dependencies: Follow these steps to install Refacer and its dependencies:
```bash ```bash
# Check if ffmpeg is available (if not, you might to download it and add it to your PATH) # Check if ffmpeg is available (if not, you might to download it and add it to your PATH)
# Windows: download ffmpeg-git-essentials.7z from https://www.gyan.dev/ffmpeg/builds/ # Windows: download ffmpeg-git-essentials.7z from https://www.gyan.dev/ffmpeg/builds/
# Other systems: see a tutorial https://www.hostinger.com/tutorials/how-to-install-ffmpeg # Other systems: see a tutorial https://www.hostinger.com/tutorials/how-to-install-ffmpeg
@@ -107,7 +107,7 @@ Follow these steps to install Refacer and its dependencies:
# For CoreML only (compatible with MacOSX, requires Silicon architecture): # For CoreML only (compatible with MacOSX, requires Silicon architecture):
pip install -r requirements-COREML.txt pip install -r requirements-COREML.txt
``` ```
For NVIDIA GPU, make sure you have both NVIDIA GPU Computing Toolkit and NVIDIA CUDNN installed. The onnxruntime-gpu version must match your version of CUDA. This example uses onnxruntime-gpu 1.21.0, which is compatible with CUDA 12.6 and CUDNN 9.4 - Refacer.py is pre-loading both libraries. Remember to update the paths if needed in refacer.py if you have different location or versions. For NVIDIA GPU, make sure you have both NVIDIA GPU Computing Toolkit and NVIDIA CUDNN installed. The onnxruntime-gpu version must match your version of CUDA. This example uses onnxruntime-gpu 1.21.0, which is compatible with CUDA 12.6 and CUDNN 9.4 - Refacer.py is pre-loading both libraries. Remember to update the paths if needed in refacer.py if you have different location or versions.

4
refacer.py
View File

@@ -30,8 +30,12 @@ gc = __import__('gc')
# Preload NVIDIA DLLs if Windows # Preload NVIDIA DLLs if Windows
if sys.platform in ("win32", "win64"): if sys.platform in ("win32", "win64"):
if hasattr(os, "add_dll_directory"): if hasattr(os, "add_dll_directory"):
try:
os.add_dll_directory(r"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin") os.add_dll_directory(r"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin")
os.add_dll_directory(r"C:\Program Files\NVIDIA\CUDNN\v9.4\bin\12.6") os.add_dll_directory(r"C:\Program Files\NVIDIA\CUDNN\v9.4\bin\12.6")
except Exception as e:
print(f"[INFO] Failed to add CUDA or CUDNN DLL directory: {e}")
print("[INFO] This error can be ignored if running in CPU mode. Otherwise, make sure the paths are correct.")
if hasattr(rt, "preload_dlls"): if hasattr(rt, "preload_dlls"):
rt.preload_dlls() rt.preload_dlls()