README.md

---
base_model:
- Qwen/Qwen2-Audio-7B-Instruct
language:
- en
library_name: transformers
pipeline_tag: audio-to-audio
tags:
- lora
license: apache-2.0
---

# StresSLM

**StresSLM** is an audio-to-audio model fine-tuned with LoRA adapters on top of the [`Qwen/Qwen2-Audio-7B-Instruct`](https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct) base model. It is designed to tackle **Sentence Stress Detection (SSD)** and **Sentence Stress Reasoning (SSR)** tasks on the StressTest benchmark.
StresSLM predicts **stress patterns** and **reasoning** based on spoken audio. 
For more information, see our paper and code:

📃 [StressTest Paper](https://arxiv.org/abs/2505.22765) | 💻 [Code](https://github.com/slp-rl/StressTest) | 🌍 [Project Page](https://pages.cs.huji.ac.il/adiyoss-lab/stresstest/) | 🤗 [StressTest Dataset](https://huggingface.co/datasets/slprl/StressTest)

---

## Usage

This model can be loaded using the HuggingFace Transformers library:

```python
from transformers import AutoProcessor, Qwen2AudioForConditionalGeneration
from peft import PeftModel, PeftConfig

# Load processor
processor = AutoProcessor.from_pretrained("Qwen/Qwen2-Audio-7B-Instruct")

# Load LoRA config and base model
peft_config = PeftConfig.from_pretrained("slprl/StresSLM")
base_model = Qwen2AudioForConditionalGeneration.from_pretrained(peft_config.base_model_name_or_path)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "slprl/StresSLM")
```

---

## Tasks

* **Sentence Stress Detection (SSD)**: Identify stressed words in an utterance.
* **Sentence Stress Reasoning (SSR)**: Reason about the speaker’s intention using stress patterns.

For evaluation scripts and benchmarks, refer to the [StressTest GitHub repository](https://github.com/slp-rl/StressTest).

---

## 📖 Citation

If you use this model, please cite:

```bibtex
@misc{yosha2025stresstest,
      title={StressTest: Can YOUR Speech LM Handle the Stress?},
      author={Iddo Yosha and Gallil Maimon and Yossi Adi},
      year={2025},
      eprint={2505.22765},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.22765},
}
```