README.md

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

# 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 was introduced in the paper: [A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation](https://huggingface.co/papers/2601.22599).

- **Developed by:** Shanda AI Research Tokyo
- **Paper:** [Hugging Face Papers](https://huggingface.co/papers/2601.22599)
- **Code Repository:** [GitHub - ShandaAI/Hive](https://github.com/ShandaAI/Hive)
- **Project Page:** [https://shandaai.github.io/Hive](https://shandaai.github.io/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

You can perform inference using the scripts provided in the official GitHub repository.

### 1) Install dependencies

```bash
pip install torch torchaudio librosa pyyaml pytorch-lightning huggingface_hub
```

### 2) FlowSep inference

Clone the [repository](https://github.com/ShandaAI/Hive) and use the `infer_flowsep.py` script, which automatically downloads the configuration and checkpoints:

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

## Citation

If you find this model or the Hive dataset useful, please cite:

```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}
}
```