sound-generation

Empirical Variational Autoencoder (EVA) is a general generative framework for continuous-valued sequences that learns autoregressive latent priors empirically from training data, alleviating the prior-posterior gap of conventional VAEs and achieving competitive generation quality with autoregressive diffusion baselines at much faster inference speed.

An open-source AI model that generates sound effects from vocal imitations and text descriptions, addressing the challenge of searching for specific sounds.