| --- |
| license: apache-2.0 |
| language: |
| - en |
| tags: |
| - audio |
| - sound-separation |
| - audio-to-audio |
| - flowsep |
| datasets: |
| - ShandaAI/Hive |
| --- |
| |
| # FlowSep-hive |
|
|
| ## Model Description |
|
|
| **FlowSep-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:** [ShandaAI/Hive](https://huggingface.co/datasets/ShandaAI/Hive) (2,442 hours of raw audio, 19.6M mixtures) |
| - **Paper:** [arXiv:2601.22599](https://arxiv.org/abs/2601.22599) |
| - **Code Repository:** [GitHub - ShandaAI/Hive](https://github.com/ShandaAI/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). |
