One of the student labs was gamified language learning - say the image in the language you are learning, and Whisper tells you whether you said it in an understandable way.
This Gradio implementation is a more polished version of their early efforts.
This says it can generate subtitle files, which is something I've wanted from whisper for a while. But does anyone know of a way to do that with just a cli tool that I can run locally? Like, ideally, just `whisper-make-subtitles ./*.mp4` to loop over every .mp4 in a directory and create matching subtitle files.
Well now I feel dumb:P In my defense, that requires finding that option (the readme doesn't discuss options) and knowing that .srt/.vtt are subtitle formats. This is great, thanks!
I've used https://github.com/tomchang25/whisper-auto-transcribe to generate subtitles and then translate them to English and it worked fairly well. It's not professional-level, but it was good enough to understand what they were saying and enjoy foreign TV.
See some of their example solutions here (along with their projects in 2022): https://id2223kth.github.io/assignments/project/ServerlessML...
One of the student labs was gamified language learning - say the image in the language you are learning, and Whisper tells you whether you said it in an understandable way.
This Gradio implementation is a more polished version of their early efforts.