---
license: mit
tags:
- dysarthric speech
- classification
- audio classification
---

# SSL4PR WavLM Base

This repository hosts the pre-trained SSL4PR WavLM Base models for Parkinson's Disease detection from speech in real-world operating conditions. These models are based on the work titled "Exploiting Foundation Models and Speech Enhancement for Parkinson’s Disease Detection from Speech in Real-World Operative Conditions" by Moreno La Quatra et al.

## Repository Link
[GitHub Repository](https://github.com/K-STMLab/SSL4PR/)

## Pre-trained Models
Pre-trained models are available on the Hugging Face model hub. To use the SSL4PR WavLM Base models, please clone the repository by running the following command:

```bash
git clone https://huggingface.co./morenolq/SSL4PR-wavlm-base
```

Ensure you have git lfs installed. Each repository contains the pre-trained models, one per fold, named `fold_1.pt`, `fold_2.pt`, ..., `fold_10.pt`.
The models are available in PyTorch format. 

- [SSL4PR WavLM Base](https://huggingface.co./morenolq/SSL4PR-wavlm-base) - **this repository**
- [SSL4PR HuBERT Base](https://huggingface.co./morenolq/SSL4PR-hubert-base)

## Citation

```bibtex
Available upon INTERSPEECH 2024 proceedings.
```