Jambi’s mission is to transcribe audio to your clipboard, as quickly and accurately as possible, while staying privacy-focused and open-source.
Jambi aims to help computer users with disabilities, such as vision or physical impairments, by providing real-time transcription of their speech. It’s also a great tool for anyone who wants to transcribe audio quickly and easily.
This is the alpha release and the project is still in early development. Currently looking for feedback and contributors. If you are a developer, you can contribute to the project by submitting pull requests or reporting issues.
If you like the project, please show your support by leaving a star. Thanks! https://github.com/guttermonk/jambi
Is there any reason you chose vosk over whisper.c++?
I’m not familiar with whisper.c++ but I did try faster-whisper. Unfortunately, the transcriptions took upward of 40sec and it didn’t offer live transcription, which is a nice feature of vosk. There’s a comparison in the readme with other differences. That said, it should be relatively modular. It shouldn’t take much to swap it back to whisper if that’s what you prefer to use. Whisper is in the nix flake as optional, and the program allows you to change models but i haven’t bothered trying to switch back to Whisper since Vosk has been more performant.
I should also add that if you don’t want to reconfigure Jambi to use Whisper, you can try WhisperNow, which is built in Python and uses Whisper. I saw similar transcription performance when I used Whisper with Jambi and decided to move forward with Vosk after testing Whisper in both programs.
Probably just playing it safe since vosk has been around longer iirc Is kinda weird to rust and not choose the more performant whisper tho