Olicorne comments

Results 659 comments of


                                            Olicorne

Feature Request + my code: audio cleanup

I notice that pydub seems to be in the requirements but is nowhere used?

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

You're mistaken, you're not inputing the modelname as Systran is just the name of the repo of the guy how makes faster whisper. I have this in my docker compose:...

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

It's probably worth adding an example in the yaml file

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

I'm not the owner of this repo so I'll leave that up to them :)

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

Well I'm definitely encountering this issue now. It happened when I switched to large v3 but might have nothing to do with that since reusing my previous config does not...

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

(Very sorry for bothering you @fedirz but because this issue was closed in the past I'm afraid you would miss it when catching up so I'm humbly notifying you and...

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

Hi everyone, I still have this issue so did a workaround: ```yaml whisper_watcher: image: docker:dind volumes: - /var/run/docker.sock:/var/run/docker.sock - ./jfk.mp3:/jfk.mp3 command: | sh -c ' docker events \ --filter "type=container"...

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

Thanks. It appears [you are right](https://github.com/speaches-ai/speaches/blob/master/src/speaches/config.py). It's too bad this feature got removed without deprecation notice nor errors though. Afaic this shouod be closed OR the feature readded.

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

I am in favour. Although my workaround is fine for my use case.

PRELOAD_MODELS doesn't work on last Docker image tag (but with build locally, it works)

Thanks for the suggestion to use lifecycle hooks, here's the updated workaround for speaches: ```yaml volumes: - ./jfk.mp3:/jfk.mp3 # for the post_start command post_start: - command: | bash -c '...