Unfortunately stable-ts and whisper don’t obviously output which files it is working on, so you’re dependent on trying to decipher it from the logs. I tried to add prints to show which files it has queued and started, but with threading, the std-out sometimes gets lost or buffered in strange ways.

Completed the Bazarr integration. See: https://github.com/McCloudS/subgen/edit/main/README.md#bazarr

I’m not sure yet. Faster-whisper has some benchmarks of the Largev2 model taking about 1 minute for 13 minutes of audio. Smaller models ought to be quicker. Unsure if the specs of the GPU will make much differenece.

It can only translate into English, but the source audio can be a foreign language.

If I knew what the endpoints were, nothing would prohibit it. I can add it to my short list.

It should detect the foreign language and make english subtitles, but I haven’t personally tried it.

I’m not using whisper.cpp anymore. I did some short comparisons between WhisperX and stable-ts and ultimately decided to go with stable-ts. Functionally, I’m sure they’re very similar.