Whisper-UI: Effortlessly Transcribe Your Audio and Video with User-Friendly GUI

5/5 - (26 votes)

Are you familiar with Whisper, the OpenAI project that enables the conversion of audio to text format? This feature is particularly useful for creating interview transcripts or video subtitles.

Exciting news! Abhay Kashyap, a coder, has developed a user interface for Whisper called Whisper-ui. This GUI utilizes Streamlit and simplifies the process of creating a list of media to translate or transcribe.

Screenshot of the Whisper-ui GUI showing an audio file being transcribed

After uploading your files, you can use the engine on the left to navigate and filter them according to your preferences. You can easily retrieve the transcripts once the files have been processed.

To install Whisper-ui, the most straightforward method is to use the provided Docker-Compose.

git clone https://github.com/hayabhay/whisper-ui.git
cd whisper-ui
docker-compose up -d

Then go to the following URL: http://localhost:8501/

Otherwise, you can also install it directly:

sudo apt install ffmpeg
pip install -r requirements.txt

And run the Python script with Streamlit:

streamlit run app/01_🏠_Home.py

To summarize, Whisper-ui is a practical tool that saves time and eliminates the need to clutter the command line. If you’re interested in exploring other projects that utilize Whisper, there’s an extensive list available here. A big thank you to Nobody for sharing this information!

+ info here.

Peggy R King

Peggy R King is a Consumer Technology Writer at Easy Tech Tutorials. In 2017, she began his writing career as a Reporter for a local media house. After two years of working in the traditional media, Peggy decided to pursue a career that combines his two passions: writing and technology.

Leave a Comment