1 مستودع
Generative architectures that use flow-matching to transform noise into continuous audio latents.
Distinct from Latent Diffusion Models: Specializes latent diffusion using flow-matching for audio signals instead of images
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Flow-Matching Audio Diffusion. Refine with filters or upvote what's useful.
Audiocraft is a deep learning audio library and machine learning framework designed for training, fine-tuning, and evaluating generative models for music and sound effects. It functions as a text-to-music generative model and a neural audio codec, providing the tools necessary to compress audio signals into discrete representations and synthesize high-fidelity waveforms from textual descriptions. The framework is distinguished by its ability to combine multiple conditioning signals, allowing for the generation of audio based on text prompts, melodic excerpts, or style-based audio clips. It al
Generates high-fidelity waveforms by learning a vector field that transforms noise into continuous audio latents.