With Python Qt 6's GUI to run Whisper for your audio files for transcription (basically Whisper with a GUI frontend).
For installing OpenTranscribe, you need to install Python 3.9.6 or higher, and PyQt6. You can install PyQt6 by running pip install PyQt6 in your terminal.
For macOS users, you can just download the .app.zip file from the releases page, anf unzip it. Then, you can run the app by double-clicking on it or moving into to the Applications folder for a permanent installation.
For usage, it's a very straightforward interface. For help on the different models, reference OpenAI's table (documentation) for help on choosing which model is best and convenient for you.
If there's any issues or a bug, please open an issue on the issues page on GitLab instance. If you have any questions, please open a discussion on the discussions page on GitHub.
(c) 2023 Abdon Morales Jr and Morales Research Corp.
This project has been archived on August 16, 2024 since pretty much OpenAI's chatGPT is as capable in its upcoming updates to do TTS or grab transcriptions from audio/video. Thus, this project is now considered obselete.
This project is based on OpenAI's Whisper