Whisper is an intuitive and powerful transcription service, capable of transcribing audio files in multiple languages such as English and German. With support for files of any size, and the ability to download transcripts as PDFs or copy them directly to the clipboard, Whisper provides a versatile solution to all your transcription needs. Moreover, the website is responsive, ensuring a seamless user experience across all devices.
- Supports multiple languages: English, German, and more.
- Transcribes audio files of any size.
- Provides results in a downloadable PDF format or copied to the clipboard.
- Website designed with a responsive interface.
Here is a quick preview of our application in action:
Here's a step-by-step guide to setting up and running the Whisper application on your machine.
Ensure you have Python and pip (Python package installer) installed on your system. If you don't have these installed, please refer to the Python official guide for installation instructions.
- Navigate to the
whisper_interfacedirectory in your terminal:cd path_to_your_directory/whisper_interface - Install the required packages using the requirements.txt file:
In case you have both Python 2 and Python 3 installed, you might need to use
pip install -r requirements.txt
pip3instead ofpip:pip3 install -r requirements.txt
- Now, you can run the application using Python:
If you have multiple versions of Python installed, you may need to specify
python main.py
python3:python3 main.py
Congratulations! You have successfully installed and run the Whisper Transcription Service. You can now upload your audio files and get them transcribed into your desired language.
If you encounter any problems or have any questions about this application, please feel free to open an issue on this repository.