Problems with CUDA and two versions of whisper on one PC

[TehMiloss]

Hey, I've recently discovered a problem with using two different versions of Whisper with CUDA.
I have installed whisperx and whisper-ctranslate2 on two different conda enviroments.

CUDA v12.5 and v11.8 are installed in Windows.
CUDNN v8.9.7 and v9.6 are installed in Windows.
Both of them are included in environment variable PATH.
Additionally I have two CUDA_PATH and CUDA_PATH_V11_8 set up.

whisperx works correctly with CUDA and spits out transcripts perfectly
whisper-ctranslate2 recognizes file but it refuses to transcript it - it crashes with no error. It only works with --device CPU argument in command line.

So, it looks like whisper-ctranslate2 has some problems with reading CUDA and CUDNN files, but I have no idea how to force it to recognize files correctly.

(I remember that on my previous Windows installation, the problem was reversed - whisper-ctranslate2 was working with CUDA and whisperx was not having any of it)

Any ideas how to fix it?

[FriedGenera]

Hey, I've recently discovered a problem with using two different versions of Whisper with CUDA. I have installed whisperx and whisper-ctranslate2 on two different conda enviroments.

CUDA v12.5 and v11.8 are installed in Windows. CUDNN v8.9.7 and v9.6 are installed in Windows. Both of them are included in environment variable PATH. Additionally I have two CUDA_PATH and CUDA_PATH_V11_8 set up.

whisperx works correctly with CUDA and spits out transcripts perfectly whisper-ctranslate2 recognizes file but it refuses to transcript it - it crashes with no error. It only works with --device CPU argument in command line.

So, it looks like whisper-ctranslate2 has some problems with reading CUDA and CUDNN files, but I have no idea how to force it to recognize files correctly.

(I remember that on my previous Windows installation, the problem was reversed - whisper-ctranslate2 was working with CUDA and whisperx was not having any of it)

Any ideas how to fix it?

AFAIK, only one CUDA is recognized at a time in Windows(though it may be possible to circumvent this in code), so you have to set the CUDA you want to use to the top of your PATH variable, change to CUDA_PATH to reflect only the one you want to use, and check using nvcc --version to make sure you're using the right version. Here's a more visual guide Make sure cuDNN 9 is installed for CUDA v12.X as ctranslate2 4.5.0 only supports 9 it seems