Full title: vocalinux : Free, open-source, 100% offline voice dictation for Linux. Is there anything better? I tried the “tiny” model—it’s not very good. Also ı will try large models some good. GitHub - VocaHQ/vocalinux: Free, open-source, 100% offline voice dictation for Linux. Speak and type anywhere via whisper.cpp, Whisper & VOSK engines, GPU-accelerated, works on X11 + Wayland!
I don’t think I’ve ever used a project like this where the tiny model is good.
If you’re just talking for voice to text, I’ve used this one for a while. Works better than the one built into my phone, and I don’t have a ton of complaints.
Orange butthole PFP detected
The tiny model is rough in pretty much everything that uses Whisper, it’s just too small. Small or medium is where it starts getting usable, and large-v3 is the good one but it wants a graphics card to be quick.
FYI, I make one of these myself, called TalkType. What fixed the accuracy problem for me was NVIDIA’s Parakeet model. It’s about as accurate as large-v3 and still fast on a regular processor with no graphics card, for English plus 24 European languages. TalkType has it as a choice, and Handy has it too. Hold-to-talk works on Wayland as well.
