Archived: The code has moved with a cleaner implementation without pytorch lightning : https://github.com/WaveGenAI/phonira
A model that can make edit of music based on a prompt. Follow MusicGen architecture.
python -m pip install -r requirements.txtThe dataset used is: https://huggingface.co/datasets/WaveGenAI/youtube-cc-by-music
python3 -m scripts.train --config_path config/config.yamlpython3 -m scripts.inference --config_path config/config.yaml --checkpoint_path PATHThen, go to http://127.0.0.1:7860
See the LICENSE file.