This is not scientific but Itook an old Xeon V4 workstation and an old Quadro GPU and compared the Whisper times for the same approximately 4 minute audio, transcribing in English. Here are the times which is slightly surpising. I used the small model with this command: whisper vid.mp4 --model small --output_format srt --language en Of course to test the GPU I added the --device cuda flag and confirmed GPU was being use........

The default version is CPU only, which usually is not what we want if we have a GPU: pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121 Now cuda enabled pytorch apps like whisper etc... can take advantage of CUDA finally! Check it is enabled False means it is not working, or at least your cuda/nvidia driver setup is installed and True means good. python3 -c........

Video Links: How To Setup 2 Phones on a Single CME Router and get the GUI going. How to use Dialpeers with CME with two routers How to implement call restrictions using COR / Class of Restriction Set your clock: HH:MM:SS clock set 22:00:00 24 September 2024........