coqui-ai / TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
http://coqui.ai
Mozilla Public License 2.0
35.07k stars 4.27k forks source link

[Bug] Docker run does not start a server on port 5002 #2250

Closed chrisbward closed 1 year ago

chrisbward commented 1 year ago

Describe the bug

Hi, Just ran the following to get the GPU server running;

docker run --rm -it -p 5002:5002 --gpus all --entrypoint /bin/bash ghcr.io/coqui-ai/tts

But it seems that I cannot connect to http://0.0.0.0:5002 in the browser.

I can confirm that the docker container is running and can interact with the terminal from the command above.

To Reproduce

Run the command;

docker run --rm -it -p 5002:5002 --gpus all --entrypoint /bin/bash ghcr.io/coqui-ai/tts

Observe that the server does not run in the browser

Expected behavior

Should be able to visit the server in the browser

Logs

No response

Environment

Docker GPU image on Ubuntu 20.04

Additional context

No response

chrisbward commented 1 year ago

Oh, checking the docs - you might want me to run python3 TTS/server/server.py --model_name tts_models/en/vctk/vits --use_cuda true to start the daemon?

I've not seen that before with containers. The services are usually running already, although I'm now hitting another problem with GPU support...

erogol commented 1 year ago

I close this one. You can create a new issue for the new one.