All notable changes to this package will be documented in this file. This package adheres to Semantic Versioning.
- Improve the stability of the GHA with testing Auido & Video Translations
- Fix project name in setup script
- Fix transaltion module import error
- Add support to download mimasa sample data
- Improve setup envrionment script
- Fix dependency issues
- Add pre-commit config to fix linting issues
- Add Django App for Mimasa to perform translations
- Add asynchronous functionality to detect faces and separate audio
- Add translation units for mimasa app and video, audio interfaces
- Improve face detection performance with asynchronous approaches added
- Document expected features and stories
- Document performance results
- Fix labeler workflow for PRs
- Added tests results for performance of face detection & audio separation
- Prepare a demo video for Mimasa Django App
- Initial implementation of Mimasa App with FaceDetector component implemented
- Implement AudioSeparator component with NUSSL Separator
- Design documentation is added including components relationship, mimasa-state behavior and sequence diagrams
- Prepared the concept of Mimasa Application