Closed jprovencher closed 5 months ago
You are supposed to run the python server outside of the docker instance with the models. Either on the backend or locally with a tunnel to the backend for ports 6006, 8888.
Got it! Maybe a future version could start the http endpoint as well internally to the docker container? Closing for now as designed.
Sample command line is missing the port forward to expose the python http.server module..
Command should be: docker run --gpus all --shm-size 64G -p 6006:6006 -p 8888:8888 -p 8000:8000 -it ghcr.io/collabora/whisperfusion:latest