Add pipeline tag and library name to metadata (#1)

- Add pipeline tag and library name to metadata (0f661f42dae95a4b7c4f0597dc194f419346d92c)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,6 +1,8 @@
 ---
 base_model:
 - Qwen/Qwen2.5-Omni-7B
+library_name: transformers
+pipeline_tag: video-text-to-text
 ---
 
 # TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
@@ -22,6 +24,7 @@ base_model:
 
 - **🌐 Project Page:** [timechat-captioner.github.io](https://timechat-captioner.github.io/) 
 - **🏠 Model:** [TimeChat-Captioner (7B)](https://huggingface.co/yaolily/TimeChat-Captioner-GRPO-7B)
+- **💻 Code:** [GitHub Repository](https://github.com/yaolinli/TimeChat-Captioner)
 - **📚 Train Dataset:** [TimeChatCap-42K](https://huggingface.co/datasets/yaolily/Timechat-OmniCaptioner-42K)
 - **🏆 Benchmark:** [OmniDCBench](https://huggingface.co/datasets/yaolily/OmniDenseCap-Benchmark)
 
@@ -129,7 +132,8 @@ with torch.inference_mode():
 
 response = processor.decode(text_ids[0][inputs.input_ids[0].size(0):], skip_special_tokens=True)
 
-print("\n" + "="*50)
+print("
+" + "="*50)
 print("🎬 VIDEO DESCRIPTION:")
 print("="*50)
 print(response)
@@ -151,4 +155,4 @@ print("="*50)
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2602.08711}
 }
-```
+```