KaraokIA

KaraokIAis a Python app to create karaoke videos using Deep Learning Models. The demo was built in gradio.

The pipeline is

• Download Youtube Video using yt-dlp

• Audio Separation using demucs

• Speech Recognition using whisperx

• Speaker Diarization (optional) pyannote

• Video with lyrics

Installation

Use the package manager pip to install the requirements.

pip install -r requirements.txt

Docker

Use docker. Under construction

docker 

Usage

python demo.py

Contributing

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.

License

GPLv3