Stable Audio Open
Abstract
Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.
Cite
@article{arxiv.2407.14358,
title = {Stable Audio Open},
author = {Zach Evans and Julian D. Parker and CJ Carr and Zack Zukowski and Josiah Taylor and Jordi Pons},
journal= {arXiv preprint arXiv:2407.14358},
year = {2024}
}
Comments
Demo: https://stability-ai.github.io/stable-audio-open-demo/ Weights: https://huggingface.co/stabilityai/stable-audio-open-1.0 Code: https://github.com/Stability-AI/stable-audio-tools. arXiv admin note: text overlap with arXiv:2404.10301