This project is a Python application for automatic transcription of audio files into text. It uses the SpeechRecognition library for transcription, and the moviepy library to extract audio from a video file.
To use this application, you must have Python 3 and the ffmpeg software suite installed:
brew install ffmpeg
- Clone this code repository using the git clone command.
- Install the dependencies using the command
pip install -r requirements.txt.
- Place the video file you want to transcribe in the downloads folder.
- Launch the transcription script by running the command python transcription.py.
- Follow the on-screen instructions to enter the name of the video.
- The transcription will be performed and the transcribed text will be saved in the downloads folder.
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.