README.md

---
language:
- en
license: cc-by-nc-4.0
tags:
- prosody
- speech
- tts
- llm
pipeline_tag: text-to-speech
---

# ProsodyLM

This repository contains the **model checkpoints and sample training data** for  
the paper [ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models](https://arxiv.org/abs/2507.20091).

## 📁 Repository structure
- `llm/`: ProsodyLM checkpoint and tokenizer
- `tts/`: TTS checkpoint and speaker embeddings
- `data/`: A small-scale sample dataset (same format as the real training data)

## 🔗 Citation
If you use this resource, please cite the paper above.

---

License: CC BY-NC 4.0