This repository has no description
Commits
Author
Commit
Message
Date
- Add vosk package (offline speech recognition based on Kaldi)
- Streaming STT that reads WAV audio from stdin
- Outputs text as sentences are recognized
- -w flag shows live words on stderr with corrections
- Supports multiple languages (en, de, fr, es, ru, cn, ja)
mumble-reminder: add 25.05 and 25.11 Release Animals