Daniel J Walsh

@ericcurtin Please update this with latest status.

This is still something that we are looking at.

We now have a PR to implement some artifact support with Podman, but this does not work with the docker model store. Meeting with Docker next week to move forward...

What version of RHEL is this? Is /var/jenkens_home a volume? If yes could you copy the file to /tmp and see if it shows up?

I am guessing /var/jenkens_home is a volume and the file is being copied but the next Run command is not seeing the copied file. In the cast of /tmp, then...

I don't know what is intended here? When you run the final build contianer, does the file show up in the volume or not, if not then I would say...

Can this be closed? Do we have this functionality now?

Yes the wav file would need to be volume mounted into the container with a :z option. Would it make sense to also allow stdin for a way file? cat...

The stdout stuff should just work, we could even just have whisper grab /dev/stdin when it sees the "-". The volume mount can also be marked ro,z so it is...

podman run --rm -i --device nvidia.com/gpu=all \ --mount=type=image,src=WHISPER.CPP-MODEL-SHORTNAME,destination=/mnt/models,rw=false,subpath=/models \ --mount=type=bind,src=/[FQual-dir-of-user-inputfilewav]/,destination=/mnt/audio/USERFILE.wav,rw=false,z \ ramalama-image /bin/sh -c "whisper-main -m /mnt/models/model.file -f /mnt/audio/USERFILE.wav"