FineFindus
FineFindus
Your reply reads like it was written by an AI. Please avoid this.
Ah Ok, I would prefer bad English (yours is not that bad) over AI output. The latter often leads to time loss, either to due to spammy output or just...
Are you using the app [MastodonRedirect](https://github.com/zacharee/MastodonRedirect)? I've had the same issue, which was caused by the app improperly relaying the URL.
1. Help is welcome :) 2. `faster_whisper` handles the download of the models. 3. see 2. 4. Should also be handled by `faster_whisper`, but I can't verify. 5. Not sure...
> There are different inputs to the WhisperModel( ) function to enable CUDA. Whisper itself has different flags to install for GPU support. I don't know enough about faster_whisper. I...
> Thoughts? If it seems like it might work, I can go ahead and work on a PR for it. Can't hurt to try. It looks relatively similar to `faster_whisper`,...
Except for the name, I can't reproduce this. The other strings are already set as translatable and often already have translation.
Ah I see, that I can indeed replicate. After failing to fix it, I've opened an issue with the Weblate support.
I tested the issue on two different devices, running Android 14 and 10. It's reproducible on the device running Android 10, but not on the one running 14.
Could you please add an example of how to recreate the problem directly with artem, as well as run the command with `--verbose trace` and include its log output here.