Skip to content
ModelListedExternal
Download

Resp Agent Models

Model weights for Resp-Agent - An intelligent respiratory sound analysis and generation system.

Sourcehuggingface.co/AustinZhang/resp-agent-models/tree/b11817df15673ccdcd3e2f8683e753bf6c3b27e2
KindOtherVersionRevision b11817d

Model source

Kind
Other
File size
345 MB–3.72 GB
Version
vRevision b11817d
Updated
Sep 13, 2026
Downloads
0
Source
Hugging Face

Source description

Resp-Agent Models

Model weights for Resp-Agent - An intelligent respiratory sound analysis and generation system.

📦 GitHub Repository: AustinZhang/Resp-Agent

📁 Contents

ModelSizeDescription
Diagnoser/checkpoints/longformer952 MBFine-tuned Longformer for EHR + audio analysis
Diagnoser/pretrained_models695 MBBEATs & Tokenizer pretrained weights
Generator/checkpoints/llm3.8 GBFine-tuned LLM for audio generation
Generator/checkpoints/flow2.0 GBCFM flow matching model
Generator/pretrained_models695 MBBEATs & Tokenizer pretrained weights
audio_descriptions.jsonl87 MB×2Audio description data

Note: DeepSeek-R1 model is NOT included here. Please download separately from:
🔗 deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

🚀 Quick Download

from huggingface_hub import snapshot_download

# Download all models
snapshot_download(
    repo_id="AustinZhang/resp-agent-models",
    local_dir="./",
    ignore_patterns=["*.md", ".gitattributes"]
)

# Download DeepSeek-R1 separately
snapshot_download(
    repo_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    local_dir="./Diagnoser/checkpoints/deepseek-r1"
)

📂 Expected Directory Structure

After downloading, your project should look like:

Resp-Agent/
├── Diagnoser/
│   ├── checkpoints/
│   │   ├── deepseek-r1/          # From deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
│   │   └── longformer/           # From this repo
│   └── pretrained_models/        # From this repo
└── Generator/
    ├── checkpoints/
    │   ├── llm/                  # From this repo
    │   └── flow/                 # From this repo
    └── pretrained_models/        # From this repo

📝 Paper

Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis (ICLR 2026)

If you find this work useful, please cite our paper:

@inproceedings{zhangresp,
  title={Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis},
  author={ZHANG, Pengfei and Xie, Tianxin and Yang, Minghao and Liu, Li},
  booktitle={The Fourteenth International Conference on Learning Representations}
}

🙏 Acknowledgements

📄 License

These model weights are released for academic research purposes only.

Sources

1 source
Hugging FacePrimaryVersion b11817df15673ccdcd3e2f8683e753bf6c3b27e2
huggingface.co/AustinZhang/resp-agent-models/tree/b11817df15673ccdcd3e2f8683e753bf6c3b27e2

Verified Sep 13

Model artifacts

5 artifacts

Diagnoser/checkpoints/longformer/best_longformer_loss_0.3374_epoch_2.pth

pth · 951 MB · SHA-256 de24ce91e39b…a134 · Hugging Face

Download

Diagnoser/pretrained_models/BEATs_iter3_plus_AS2M.pt

pt · 345 MB · SHA-256 d43cbfad4d7b…8d34 · Hugging Face

Download

Generator/checkpoints/flow/best_ep5_val_loss_0.0638_step164485.pt

pt · 1.96 GB · SHA-256 e496c66ed429…beea · Hugging Face

Download

Generator/checkpoints/llm/best_model_loss_1.2393_epoch_3.pth

pth · 3.72 GB · SHA-256 f4d6f8f0e0f0…1d1f · Hugging Face

Download

Generator/pretrained_models/BEATs_iter3_plus_AS2M.pt

pt · 345 MB · SHA-256 d43cbfad4d7b…8d34 · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 13huggingface.co/AustinZhang/resp-agent-models

--- license: mit tags: - respiratory-sound - medical-ai - audio-generation - audio-classification language: - en --- # Resp-Agent Models Model weights for **Resp-Agent** - An intelligent respiratory sound analysis and generation system. 📦 **GitHub Repository**: [AustinZhang/Resp-Agent](https://github.com/zpforlove/Resp-Agent) ## 📁 Contents | Model | Size | Description | |-------|------|-------------| | **Diagnoser/checkpoints/longformer** | 952 MB | Fine-tuned Longformer for EHR + audio analysis | | **Diagnoser/pretrained_models** | 695 MB | BEATs & Tokenizer pretrained weights | | **Generator/checkpoints/llm** | 3.8 GB | Fine-tuned LLM for audio generation | | **Generator/checkpoints/flow** | 2.0 GB | CFM flow matching model | | **Generator/pretrained_models** | 695 MB | BEATs & Tokenizer pretrained weights | | **audio_descriptions.jsonl** | 87 MB×2 | Audio description data | > **Note**: DeepSeek-R1 model is **NOT** included here. Please download separately from: > 🔗 [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) ## 🚀 Quick Download ```python from huggingface_hub import snapshot_download # Download all models snapshot_download( repo_id="AustinZhang/resp-agent-models", local_dir="./", ignore_patterns=["*.md", ".gitattributes"] ) # Download DeepSeek-R1 separately snapshot_download( repo_id="deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", local_dir="./Diagnoser/checkpoints/deepseek-r1" ) ``` ## 📂 Expected Directory Structure After downloading, your project should look like: ``` Resp-Agent/ ├── Diagnoser/ │ ├── checkpoints/ │ │ ├── deepseek-r1/ # From deepseek-ai/DeepSeek-R1-Distill-Qwen-7B │ │ └── longformer/ # From this repo │ └── pretrained_models/ # From this repo └── Generator/ ├── checkpoints/ │ ├── llm/ # From this repo │ └── flow/ # From this repo └── pretrained_models/ # From this repo ``` ## 📝 Paper **[Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis](https://openreview.net/forum?id=ZkoojtEm3W&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DICLR.cc%2F2026%2FConference%2FAuthors%23your-submissions))** (ICLR 2026) If you find this work useful, please cite our paper: ```bibtex @inproceedings{zhangresp, title={Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis}, a...

NoteSep 13huggingface.co/AustinZhang/resp-agent-models

Source context: 0 downloads · 0 likes · Pipeline audio-classification · Repo AustinZhang/resp-agent-models