MusicGen

Parameters

3.4B

Published

Jun 8, 2023

MusicGen is an AI model developed by Meta AI (United States), first published in June 2023. It works in the audio domain, on tasks such as audio generation.

Epoch AI has no training-compute estimate for this model. The model has 3,359,000,000 parameters. It was trained on roughly 14.3T datapoints.

Access: Open weights (non-commercial). Its weights are openly available. The reference paper has 665 citations. Epoch AI rates the confidence of this record as likely.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Audio
Task: Audio generation
Parameters: 3,359,000,000
Dataset size: 14.3T
Numerical format: FP16
Model accessibility: Open weights (non-commercial)
Open weights: Yes
Citations: 665
Epoch confidence: Likely