Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] Unable to start transcription with large video files. #102

Open
Davide9908 opened this issue Jun 2, 2024 · 4 comments
Open

[BUG] Unable to start transcription with large video files. #102

Davide9908 opened this issue Jun 2, 2024 · 4 comments

Comments

@Davide9908
Copy link

Davide9908 commented Jun 2, 2024

Hi, i'm trying to transcribe a large file (3h of gameplay, 13.4 GB) but the file is stuck on "Waiting for transcription..."
Once the file is uploaded the web page first returns an error:
image

then after a couple of second the "backend" process inside the container crashes and it is restarted with the following logs:
image

I'm runnning docker in Windows 11 using a Nvidia gpu

I think this issue may be related to #79

@Satanic-Spirit
Copy link

I'm facing the same issue. It seems that if I send a bigger file the backend crashes.

@Satanic-Spirit
Copy link

I looked into it further and found out that Whishper docker was using too much ram and the kernel was killing the process. I tried to put the limits but no success. Is there any way to limit the memory usage and then restart the job from same point?

@Steltek
Copy link

Steltek commented Oct 20, 2024

Have you tried rendering out just the audio from the video and uploading just that? (If the memory usage comes from the file getting loaded into RAM somewhere, this should drastically reduce it.)

@Satanic-Spirit
Copy link

I can give that a shot, but I'm running 16 GB ram on the system with proxmox needing like 1 to operate. Even if a video file is 2 GB it should have sufficient memory but it skyrockets like no tomorrow.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants