Update app.py

app.py

@@ -207,63 +207,59 @@ footer {
 """
 
 with gr.Blocks(css=css) as demo:
-
-
-        with gr.Row():
-        
-            with gr.Column():
-                video_in = gr.Video(sources=["upload"], label="Video input")
-                with gr.Row():
-                    chosen_model = gr.Dropdown(label="Choose a model", choices=["MAGNet", "AudioLDM-2", "AudioGen", "Tango"], value="Tango")
-                    submit_btn = gr.Button("Submit", scale=0)
-            with gr.Column():
-                caption_o = gr.Textbox(label="Scene caption", interactive=False)
-                retry_btn = gr.Button("Retry with edited scene caption", interactive=False)
-                audio_o = gr.Audio(label="Audio output")
+    with gr.Row():
+        with gr.Column():
+            video_in = gr.Video(sources=["upload"], label="Video input")
+            with gr.Row():
+                chosen_model = gr.Dropdown(label="Choose a model", choices=["MAGNet", "AudioLDM-2", "AudioGen", "Tango"], value="Tango")
+                submit_btn = gr.Button("Submit", scale=0)
         with gr.Column():
-            video_o = gr.Video(label="Video with soundFX")
+            caption_o = gr.Textbox(label="Scene caption", interactive=False)
+            retry_btn = gr.Button("Retry with edited scene caption", interactive=False)
+            audio_o = gr.Audio(label="Audio output")
+    with gr.Column():
+        video_o = gr.Video(label="Video with soundFX")
 
-        gr.Examples(
-            examples = [
-                ["examples/photoreal-train.mp4", "Tango"], 
-                ["examples/train-window.mp4", "Tango"], 
-                ["examples/chinese-new-year-dragon.mp4", "Tango"], 
-                ["examples/big-sur.mp4", "AudioLDM-2"]
-            ],
-            fn=infer,
-            inputs = [video_in, chosen_model],
-            outputs= [caption_o, retry_btn, audio_o, video_o],
-            #cache_examples=True
-        )
+    gr.Examples(
+        examples=[
+            ["examples/photoreal-train.mp4", "Tango"], 
+            ["examples/train-window.mp4", "Tango"], 
+            ["examples/chinese-new-year-dragon.mp4", "Tango"], 
+            ["examples/big-sur.mp4", "AudioLDM-2"]
+        ],
+        fn=infer,
+        inputs=[video_in, chosen_model],
+        outputs=[caption_o, retry_btn, audio_o, video_o]
+    )
 
     video_in.change(
-        fn = refresh,
-        inputs = None,
-        outputs = [caption_o, retry_btn, audio_o, video_o],
-        queue = False,
-        show_progress = False
+        fn=refresh,
+        inputs=None,
+        outputs=[caption_o, retry_btn, audio_o, video_o],
+        queue=False,
+        show_progress=False
     )
 
     video_in.clear(
-        fn = refresh,
-        inputs = None,
-        outputs = [caption_o, retry_btn, audio_o, video_o],
-        queue = False,
-        show_progress = False
+        fn=refresh,
+        inputs=None,
+        outputs=[caption_o, retry_btn, audio_o, video_o],
+        queue=False,
+        show_progress=False
     )
-    
+
     submit_btn.click(
         fn=infer,
         inputs=[video_in, chosen_model],
         outputs=[caption_o, retry_btn, audio_o, video_o],
-        concurrency_limit = 2
+        concurrency_limit=2
     )
 
     retry_btn.click(
         fn=retry,
         inputs=[caption_o, video_in, chosen_model],
         outputs=[audio_o, video_o],
-        concurrency_limit = 2
+        concurrency_limit=2
     )
 
-demo.queue(max_size=10).launch(show_api=False, debug=True, show_error=True)
+demo.queue(max_size=10).launch(show_api=False, debug=True, show_error=True)