arXiv · 2611.11592
LAION-Audio-XL: A Web-Scale Corpus and Scaling Studies for Contrastive Language-Audio Pretraining
Abstract
Recent progress on contrastive audio-language models can be attributed mainly to the scale and quality of their training data. Larger training datasets expose models to a broader range of sounds and corresponding audio captions. To exploit this, we collect 1.48 billion audio samples from academic datasets, internet datasets, web collections, Common Crawl, and YouTube, and process them with a multi-stage curation pipeline. Furthermore, we generate short and long captions for samples in our corpus that lack them. We use our dataset to study the scaling behavior of contrastive audio-language models based on the NaFlex architecture for the audio encoder. Our experiments identify trade-offs between model size and training data for a given compute budget. Moreover, our resulting models, CLAP2, outperform prior audio-text models of comparable size on the MAEB and HEAR benchmarks. We release our dataset, captions, model checkpoints, and code.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Gijs Wijngaard, Felix Förster, Ross Wightman, Marianna Nezhurina, Christoph Schuhmann, Jenia Jitsev, A. Sophia Koepke. 2026-11-08. LAION-Audio-XL: A Web-Scale Corpus and Scaling Studies for Contrastive Language-Audio Pretraining. https://searcharxiv.com/abs/2611.11592
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.