Task
Text To Audio
M
facebook/musicgen-small
Text To Audio·facebook· 322.1K· 495
MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts. It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebo
# pull & run locally
pip install mlforge-sdk && mlforge pull facebook/musicgen-small
pip install mlforge-sdk && mlforge pull facebook/musicgen-small
Model details
Provider
facebook
Framework
transformers
Parameters
591.1M
Size
9.8 GB
License
cc-by-nc-4.0
Downloads
322.1K
Likes
495
Paper
arXiv:2306.05284
Updated
2023-11-17
About facebook/musicgen-small
MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts. It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio.