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........
A lot of companies are unsure which solution to choose and many may not be aware of Docker Swarm as an alternative to Kubernetes. One thing that many Sysadmins find is that Docker Swarm is simply easier, quicker to setup and maintain by far than Kubernetes.........
You need to disable vsync like this when running glxgears:
vblank_mode=0 glxgears
For Nvidia drivers do this:
__GL_SYNC_TO_VBLANK=0 glxgears
Notice the higher than 59-60 fps results with vblank_mode=0:
ATTENTION: default value of option vblank_mode overridden by environment.
7919 frames in 5.0 seconds = 1583.704 FPS
8187 frames in 5.0 seconds = 1637.266 FPS........