You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
![]() also replace back arrow with globe (for IME switching) |
2 years ago | |
---|---|---|
app | 2 years ago | |
gradle/wrapper | 2 years ago | |
.gitignore | 2 years ago | |
LICENSE | 2 years ago | |
README.md | 2 years ago | |
build.gradle | 2 years ago | |
gradle.properties | 2 years ago | |
gradlew | 2 years ago | |
gradlew.bat | 2 years ago | |
settings.gradle | 2 years ago |
README.md
About
This project implements offline speech recognition for Android using the vosk API.
Roadmap (in no particular order)
- speech input support
- multiple languages support
- multiple models for the same language (with grammars?)
- link the settings activity to the speech input settings (android system settings)
- make the app build reproducible
- (maybe) register to handle zip files and decompress the models
- (maybe) allow to delete installed models
- (maybe) add a speech IME
Contributing
This is a project I work on in my spare time, for my own use case and with my own schedule and priorities. Maintaining a community project is a hard work, that I know for having helped in doing it in the past. I am not looking forward to repeating that experience right now. This is the reason of issues and PR being closed in this repository.