Update app.py

app.py

@@ -90,7 +90,7 @@ with gr.Blocks() as demo:
 
     Notably, Aero-1-Audio excels at lossless ASR on ultra-long audio—up to 16 minutes—without the need for audio segmentation.
 
-    [📚 Blog](https://www.lmms-lab.com/posts/aero_audio/) | [🤗 Model Checkpoints](https://huggingface.co/lmms-lab/Aero-1-Audio-1.5B) | [📖 Evaluation Results](https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/658) | [📚 Cookbook](https://www.lmms-lab.com/posts/lmms-lab-docs/aero_audio/)
+    [Github](https://github.com/EvolvingLMMs-Lab/Aero-1/blob/main/README.md) | [Playground](https://huggingface.co/spaces/lmms-lab/Aero-1-Audio-Demo) | [Model Checkpoints](https://huggingface.co/lmms-lab/Aero-1-Audio-1.5B) | [Evaluation Results](https://github.com/EvolvingLMMs-Lab/lmms-eval/pull/658) | [Cookbook](https://www.lmms-lab.com/posts/lmms-lab-docs/aero_audio/)
 
     To explore its capabilities, you can upload your own audio or record your voice directly.
     Or simply start by trying the example demo below.