AudioSep Hive

--- license: apache-2.0 language: - en tags: - audio - sound-separation - audio-to-audio - audiosep datasets: - JusperLee/Hive-ALL --- # AudioSep-hive ## Model Description **AudioSep-hive** is a data-efficient, query-based universal sound separation model trained on the [Hive dataset](https://huggingface.co/datasets/ShandaAI/Hive). By leveraging the high-quality, semantically consistent Hive dataset, this model achieves competitive separation accuracy and perceptual quality comparable to state-of-the-art models (such as SAM-Audio) while utilizing only a fraction (~0.2%) of the training data volume. This model is developed by **Shanda AI Research Tokyo** and is introduced in the paper: [A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation](https://arxiv.org/abs/2601.22599). ## Model Details - **Model Type:​** Query-Based Universal Sound Separation - **Language(s):​** English (for text queries) - **License:​** Apache 2.0 (Please update if different) - **Trained on:​** [JusperLee/Hive](https://huggingface.co/datasets/JusperLee/Hive-ALL) (2,442 hours of raw audio, 19.6M mixtures) - **Paper:​** [arXiv:2601.22599](https://arxiv.org/abs/2601.22599) - **Code Repository:​** [GitHub - JusperLee/Hive](https://github.com/JusperLee/Hive) ## Uses The model is intended for universal sound separation tasks, allowing users to extract specific sounds from complex audio mixtures using multimodal prompts (e.g., text descriptions or audio queries).

Source context: 69 downloads · 1 likes · Pipeline audio-to-audio · Repo JusperLee/AudioSep-hive

Source context: 23 downloads · 0 likes · Pipeline audio-to-audio · Repo JusperLee/AudioSep-hive