We released a new version of ReaSpeech, 0.5.0, to Docker Hub! >>
hub.docker.com/r/techaudiodo…
Changes in this release:
- Configurable font size
- Improved export interface
- Added support for whisper.cpp ASR engine
- Better process handling when running outside of Docker
- Removed dependency on Redis
- Usability & reliability improvements
This technically means GPU transcription is now supported on Apple Silicon! Stay tuned for more details and config details as we improve our docs.
(video description: demo of configurable font sizes, no audio)