The International Storytelling Center has amassed a vast collection of audio files, and transcribing them manually can be time-consuming and tedious. This Python-based project automates the transcription process using Whisper, an advanced Open AI technology that can transcribe and translate audio files with high accuracy. With this tool, the International Storytelling Center can easily convert their audio files into text format, saving valuable time and resources.
- Clone the repository:
git clone https:/rubenmaharjan/isc-transcription.git- Navigate to the cloned directory:
cd isc-transcription- Install the required packages:
pip install -r requirements.txt- Run the program:
python main.pyTo run the transcription process, follow these steps:
-
Open a terminal and navigate to the project directory.
-
Make sure you have activated the virtual environment (if you are using one).
-
Run the following command to start the transcription process:
python main.pyThis will run the transcription process based on the configuration that has been created.
- Once the process is complete, the transcribed text will be saved to a text file in the output directory.
Note: Make sure to update the configuration file (config.xml) with the correct settings before running the code. You can also specify the audio files you want to transcribe by adding their file paths to the audio_files list in main.py.
If you encounter any issues or have any questions, please refer to the Contributing Guidelines or contact the project maintainers.
We would like to express our gratitude to the following individuals and organizations who contributed to this project:
- Phil Pfeiffer, who provided valuable feedback and testing for the code.
- The International Storytelling Center, who provided the audio files used in the project.
- OpenAI, who developed the Whisper tool used for transcription.
- The Python community, for their invaluable resources and support.
Thank you all for your help and support!