A free, open source, and extensible speech-to-text application that works completely offline.
Commits on main
fix: auto-unload model after idle timeout to reduce memory (#1051)
d1da935 Viren Mohindra committed 8 months ago
feat(nix): NixOS integration — ALSA_PLUGIN_DIR, nixosModule, home-manager module (#1025)
cf284b1 COGnITO (mode: carbon) committed 8 months ago
experimental: pick between cpu/gpu acceleration + enable directml on windows (#1058)
cafc2b7 CJ Pais committed 8 months ago
Migrate to transcribe-rs-0.3.1 and add Canary support (#1023)
f8bbcd7 Ivan Zhuravlev committed 8 months ago
Remove `step` prop from VolumeSlider component (#944)
e3a040c Scott Humphries committed 8 months ago
feat: pass custom words as Whisper initial_prompt instead of post-correction (#1035)
85a8ed7 Javier Campanini committed 8 months ago
fix(nix): replace manual hash management with bun2nix (#1021)
7056edc Evgeny Khudoba committed 8 months ago
fix(nix): Fixed nix hash for dependencies, added CI job and script for updating dependencies versions (#948)
5dbe99b Evgeny Khudoba committed 8 months ago
Add model loading failure notifications with i18n support (#997)
82297fa CJ Pais committed 8 months ago
ui: improve scrollbar UI with custom colors and rounded thumb (#983)
d6ed1f9 Arshit Vaghasiya committed 8 months ago