facebook/musicgen-small is Meta's compact version of the MusicGen model capable of generating high-quality music from text prompts. It uses a single-stage autoregressive transformer and can produce coherent musical pieces up to several minutes long. The model is distributed on Hugging Face and integrates with the Transformers library.
In the Voice, TTS & speech space, Musicgen Small takes a focused approach. It focuses on generating original music tracks from text descriptions using a compact autoregressive model. It is built as an open-source project for developers. Musicgen Small is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
It is developed by Meta, and the product first shipped in 2018. Development happens publicly on GitHub with 162.8k stars and 744 commits in the last 90 days. Key capabilities include Music Generation, text-to-Music, and Audio Synthesis.
Latest indexed changes and source events
facebook/musicgen-small verified by the PulseGate indexer
Other apps tracked under the same category.
