Add link to HF paper page

This PR adds a link to the paper page on the Hugging Face Hub in the model card content, making the paper easier to find. The existing metadata is kept unchanged because the full speech interface relies on the custom `textpro_slm` package rather than a standard Transformers loading path.

README.md

@@ -1,14 +1,14 @@
 ---
-license: other
-license_name: qwen-research
-license_link: https://huggingface.co/qqjz/TextPro-SLM-3B-Global/blob/main/LICENSE
 base_model:
 - Qwen/Qwen2.5-3B-Instruct
 - qqjz/WhisperPro
-library_name: pytorch
-pipeline_tag: audio-text-to-text
 language:
 - en
+library_name: pytorch
+license: other
+license_name: qwen-research
+license_link: https://huggingface.co/qqjz/TextPro-SLM-3B-Global/blob/main/LICENSE
+pipeline_tag: audio-text-to-text
 tags:
 - textpro-slm
 - speech-language-model
@@ -16,6 +16,7 @@ tags:
 - audio
 - global-prepending
 ---
+
 # TextPro-SLM-3B-Global
 
 **Your speech LLM can be a prosody-aware text LLM.**
@@ -24,7 +25,7 @@ tags:
 
 TextPro-SLM brings speech closer to a text LLM's native input format: transcript tokens carry linguistic content, and compact prosody embeddings carry complementary acoustic information. The paper studies how this input-side factorization preserves semantic capabilities while learning paralinguistic understanding with roughly **1,000 hours of LLM training audio**.
 
-[Paper](https://openreview.net/forum?id=Jsjmo8eX29) · [GitHub project](https://github.com/dreamtheater123/TextPro-SLM) · [Paired WhisperPro](https://huggingface.co/qqjz/WhisperPro)
+[Paper](https://openreview.net/forum?id=Jsjmo8eX29) · [GitHub project](https://github.com/dreamtheater123/TextPro-SLM) · [Paired WhisperPro](https://huggingface.co/qqjz/WhisperPro) · [Hugging Face Paper](https://huggingface.co/papers/2605.05927)
 
 ## Checkpoint
 
@@ -90,4 +91,4 @@ The paired WhisperPro derives from OpenAI Whisper large-v3 and has its own Apach
   year={2026},
   url={https://openreview.net/forum?id=Jsjmo8eX29}
 }
-```
+```