README.md

---
datasets:
- ShandaAI/Hive
language:
- en
license: apache-2.0
pipeline_tag: audio-to-audio
tags:
- audio
- sound-separation
- audiosep
---

# AudioSep-hive

**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.

- **Paper:** [A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation](https://arxiv.org/abs/2601.22599)
- **Project Page:** https://shandaai.github.io/Hive
- **Code Repository:** https://github.com/ShandaAI/Hive

## Model Details

- **Model Type:** Query-Based Universal Sound Separation
- **Language(s):** English (for text queries)
- **License:** Apache 2.0
- **Trained on:** [ShandaAI/Hive](https://huggingface.co/datasets/ShandaAI/Hive) (2,442 hours of raw audio, 19.6M mixtures)

## 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). 

## Usage

To use this model, you can use the inference scripts provided in the official GitHub repository.

### 1. Install dependencies

```bash
git clone https://github.com/ShandaAI/Hive
cd Hive
pip install torch torchaudio librosa pyyaml pytorch-lightning huggingface_hub gradio
```

### 2. Run Inference

The following command will automatically download the configuration and checkpoints from this repository:

```bash
python infer_audiosep.py \
  --audio_file /path/to/mixture.wav \
  --text "acoustic guitar" \
  --output_file /path/to/audiosep_output.wav
```

## Citation

```bibtex
@article{li2026semantically,
  title={A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation},
  author={Li, Kai and Cheng, Jintao and Zeng, Chang and Yan, Zijun and Wang, Helin and Su, Zixiong and Zheng, Bo and Hu, Xiaolin},
  journal={arXiv preprint arXiv:2601.22599},
  year={2026}
}
```