Add library name and update pipeline tag

README.md

@@ -1,15 +1,16 @@
 ---
-license: apache-2.0
 language:
-  - zh
-  - en
+- zh
+- en
+license: apache-2.0
+pipeline_tag: audio-text-to-text
+library_name: transformers
 tags:
-  - tts
-  - speech-evaluation
-  - continuation-score
-  - role-play
-  - reward-model
-pipeline_tag: text-to-speech
+- tts
+- speech-evaluation
+- continuation-score
+- role-play
+- reward-model
 ---
 
 <h1 align="center">
@@ -29,7 +30,7 @@ pipeline_tag: text-to-speech
 </p>
 
 <p align="center">
-📑 <a href="https://arxiv.org/abs/2601.22661">Paper</a> &nbsp;|&nbsp;
+📑 <a href="https://huggingface.co/papers/2601.22661">Paper</a> &nbsp;|&nbsp;
 💻 <a href="https://github.com/y-ren16/MCLP">Code</a> &nbsp;|&nbsp;
 📊 <a href="https://huggingface.co/datasets/y-ren16/WenetSpeech-RP">Dataset</a> &nbsp;|&nbsp;
 🗣️ <a href="https://huggingface.co/y-ren16/MCLP-RPTTS">MCLP-RPTTS Model</a>
@@ -43,11 +44,7 @@ The MCLP metric serves as both:
 1. **An evaluation metric** for role-play TTS quality (correlation with human MOS: Spearman ρ = 0.94)
 2. **A reward signal** for GRPO-based reinforcement learning to improve TTS expressiveness
 
-This model is presented in:
-
-> **Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability**
-> *Yong Ren\*, Jingbei Li\*, Haiyang Sun, Yujie Chen, Cheng Yi, Yechang Huang, Hao Gu, Ye Bai, Xuerui Yang*
-> ICML 2026
+This model is presented in the paper [Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability](https://huggingface.co/papers/2601.22661).
 
 ## How MCLP Works
 
@@ -123,4 +120,4 @@ This model is released under the [Apache 2.0 License](LICENSE).
 This project builds upon:
 - [Step-Audio 2](https://github.com/stepfun-ai/Step-Audio2)
 - [CosyVoice](https://github.com/FunAudioLLM/CosyVoice)
-- [FlashCosyVoice](https://github.com/xingchensong/FlashCosyVoice)
+- [FlashCosyVoice](https://github.com/xingchensong/FlashCosyVoice)