https://github.com/WaveGenAI/WaveAI

A model that can generate music based on prompt and lyrics.
https://github.com/WaveGenAI/WaveAI

deep-learning generative-ai huggingface implementation music pytorch transformer

Last synced: 3 days ago
JSON representation

A model that can generate music based on prompt and lyrics.

• Host: GitHub
• URL: https://github.com/WaveGenAI/WaveAI
• Owner: WaveGenAI
• License: apache-2.0
• Archived: true
• Created: 2024-01-14T20:44:58.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-11-30T17:54:24.000Z (2 months ago)
• Last Synced: 2024-11-30T18:34:11.413Z (2 months ago)
• Topics: deep-learning, generative-ai, huggingface, implementation, music, pytorch, transformer
• Language: Python
• Homepage: https://amplified-people-d16.notion.site/WaveAI-0a6788b7ebeb43a39babcf7431375ca5
• Size: 251 KB
• Stars: 5
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• project-awesome - WaveGenAI/WaveAI - A model that can generate music based on prompt and lyrics. (Python)

README

        
# **Archived: The code has moved with a cleaner implementation without pytorch lightning : https://github.com/WaveGenAI/phonira**

# WaveAI

A model that can make edit of music based on a prompt. Follow MusicGen architecture.

# Installation

```py

python -m pip install -r requirements.txt

```

# Dataset

The dataset used is: https://huggingface.co/datasets/WaveGenAI/youtube-cc-by-music

# Launch the trainig

```py

python3 -m scripts.train --config_path config/config.yaml

```

# Run inference

```py

python3 -m scripts.inference --config_path config/config.yaml --checkpoint_path PATH

```

Then, go to http://127.0.0.1:7860

# License

See the LICENSE file.