Add requirements.txt

app.py

@@ -72,10 +72,9 @@ def greet(image, audio):
 
 
 title = "Zero-shot sound source localization with ACL"
-description = "This is simple demo of our WACV'24 paper 'Can CLIP Help Sound Source Localization?'\n"
-description += "To use it, simply upload an image and corresponding audio to mask (identify in the image)"
-description += "or use one of the examples below and click 'submit'. Results will show up in a few seconds."
+description = "This is simple demo of our WACV'24 paper 'Can CLIP Help Sound Source Localization?'\nTo use it, simply upload an image and corresponding audio to mask (identify in the image) or use one of the examples below and click 'submit'. Results will show up in a few seconds."
 
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2311.04066'>Can CLIP Help Sound Source Localization?</a> | <a href='https://github.com/swimmiing/ACL-SSL'>Official Github Repository</a></p>"
 
 demo = gr.Interface(
     fn=greet,
@@ -83,6 +82,7 @@ demo = gr.Interface(
     outputs=gr.Image(type="pil"),
     title=title,
     description=description,
+    article=article,
 )
 
 demo.launch(debug=True)

requirements.txt

@@ -2,4 +2,5 @@ torch==1.13
 torchvision==0.14.0
 torchaudio==0.13.0
 transformers==4.25.1
-Pillow
+Pillow
+opencv-python