You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
But i can't get this to run at all. I have tried manually installing CUDA and CUDNN in various types of ways manually as well, setting the path variables myself, but it never works and fails with this:
`whispersubs.exe "Z:\series\The Queen's Gambit\Season 1\The Queen's Gambit - S01E01 - Openings WEBRip-1080p.mkv"
C:\Users\Administrator\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.12_qbz5n2kfra8p0\LocalCache\local-packages\Python312\site-packages\whispersubs\__main__.py:32: UserWarning: NVIDIA CUDA libraries not found, inference will run on CPU only.
warnings.warn("NVIDIA CUDA libraries not found, inference will run on CPU only.", stacklevel=1)
0.3s [I] (whispersubs) Opening input file 'Z:\series\The Queen's Gambit\Season 1\The Queen's Gambit - S01E01 - Openings WEBRip-1080p.mkv'
transcribing 0%| | 0.00/3552.80s [00:00<?, 0.0x realtime]Could not locate cudnn_ops64_9.dll. Please make sure it is in your library path!
Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor`
It can't find the cudnn_ops64_9.dll under any circumstances. The command import nvidia.cudnn.lib works. However this:
import nvidia.cublas.lib
Traceback (most recent call last):
File "", line 1, in
ModuleNotFoundError: No module named 'nvidia.cublas.lib'
Maybe I'm just failing at basic things here, but i could not get this to work. Any help would be highly appreciated.
The text was updated successfully, but these errors were encountered:
I installed like this
py -m pip install 'whispersubs[cuda]@git+https://github.com/andreabak/whispersubs.git'
But i can't get this to run at all. I have tried manually installing CUDA and CUDNN in various types of ways manually as well, setting the path variables myself, but it never works and fails with this:
It can't find the cudnn_ops64_9.dll under any circumstances. The command import nvidia.cudnn.lib works. However this:
The text was updated successfully, but these errors were encountered: