.

app.py

@@ -60,15 +60,15 @@ def create_ui(examples_path: str):
                         label=f"Highlights ({format_duration(example['highlights']['duration_seconds'])})",
                         interactive=False
                     )
-                    with gr.Accordion("Model chain of thought details", open=False):
-                        gr.Markdown(f"#Summary: {example['analysis']['video_description']}")
-                        gr.Markdown(f"#Highlights to search for: {example['analysis']['highlight_types']}")
+                    with gr.Accordion("Chain of thought details", open=False):
+                        gr.Markdown(f"### Summary: {example['analysis']['video_description']}")
+                        gr.Markdown(f"### Highlights to search for: {example['analysis']['highlight_types']}")
 
         gr.Markdown("## Try It Yourself!")
         with gr.Row():
             with gr.Column(scale=1):
                 input_video = gr.Video(
-                    label="Upload your video (max 20 minutes)",
+                    label="Upload your video (max 30 minutes)",
                     interactive=True
                 )
                 process_btn = gr.Button("Process Video", variant="primary")
@@ -83,7 +83,7 @@ def create_ui(examples_path: str):
                 status = gr.Markdown()
         
                 analysis_accordion = gr.Accordion(
-                    "Model chain of thought details", 
+                    "Chain of thought details", 
                     open=True, 
                     visible=False
                 )
@@ -106,9 +106,9 @@ def create_ui(examples_path: str):
             
             try:
                 duration = get_video_duration_seconds(video)
-                if duration > 1200:  # 20 minutes
+                if duration > 1800:  # 30 minutes
                     yield [
-                        "Video must be shorter than 20 minutes",
+                        "Video must be shorter than 30 minutes",
                         "",
                         "",
                         gr.update(visible=False),
@@ -122,14 +122,14 @@ def create_ui(examples_path: str):
                     "",
                     "",
                     gr.update(visible=False),
-                    gr.update(visible=True)
+                    gr.update(visible=False)
                 ]
 
                 model, processor = load_model()
                 detector = BatchedVideoHighlightDetector(
                     model, 
                     processor, 
-                    batch_size=8
+                    batch_size=12
                 )
 
                 yield [
@@ -141,7 +141,7 @@ def create_ui(examples_path: str):
                 ]
                 
                 video_desc = detector.analyze_video_content(video)
-                formatted_desc = f"#Summary: {video_desc[:500] + '...' if len(video_desc) > 500 else video_desc}"
+                formatted_desc = f"### Summary: {video_desc[:500] + '...' if len(video_desc) > 500 else video_desc}"
                 
                 yield [
                     "Determining highlight types...",
@@ -152,7 +152,7 @@ def create_ui(examples_path: str):
                 ]
                 
                 highlights = detector.determine_highlights(video_desc)
-                formatted_highlights = f"#Highlights to search for: {highlights[:500] + '...' if len(highlights) > 500 else highlights}"
+                formatted_highlights = f"### Highlights to search for: {highlights[:500] + '...' if len(highlights) > 500 else highlights}"
                 
                 # Get all segments
                 segments = get_fixed_30s_segments(video)
@@ -223,137 +223,6 @@ def create_ui(examples_path: str):
         )
 
     return app
-    #     gr.Markdown("## Try It Yourself!")
-    #     with gr.Row():
-    #         with gr.Column(scale=1):
-    #             input_video = gr.Video(
-    #                 label="Upload your video (max 20 minutes)",
-    #                 interactive=True
-    #             )
-    #             process_btn = gr.Button("Process Video", variant="primary")
-            
-    #         with gr.Column(scale=1):
-    #             output_video = gr.Video(
-    #                 label="Highlight Video",
-    #                 visible=False,
-    #                 interactive=False,
-    #             )
-
-    #             status = gr.Markdown()
-        
-    #             analysis_accordion = gr.Accordion(
-    #                 "Model chain of thought details", 
-    #                 open=True, 
-    #                 visible=False
-    #             )
-                
-    #             with analysis_accordion:
-    #                 video_description = gr.Markdown("", elem_id="video_desc")
-    #                 highlight_types = gr.Markdown("", elem_id="highlight_types")
-
-    #     @spaces.GPU
-    #     def on_process(video):
-    #         if not video:
-    #             yield [
-    #                 "Please upload a video",  # status
-    #                 "",  # video_description
-    #                 "",  # highlight_types
-    #                 gr.update(visible=False),  # output_video
-    #                 gr.update(visible=False)  # analysis_accordion
-    #             ]
-    #             return
-            
-    #         try:
-    #             duration = get_video_duration_seconds(video)
-    #             if duration > 1200:  # 20 minutes
-    #                 yield [
-    #                     "Video must be shorter than 20 minutes",
-    #                     "",
-    #                     "",
-    #                     gr.update(visible=False),
-    #                     gr.update(visible=False)
-    #                 ]
-    #                 return
-
-    #             # Make accordion visible as soon as processing starts
-    #             yield [
-    #                 "Loading model...",
-    #                 "",
-    #                 "",
-    #                 gr.update(visible=False),
-    #                 gr.update(visible=True)
-    #             ]
-
-    #             model, processor = load_model()
-    #             detector = BatchedVideoHighlightDetector(model, processor, batch_size=8)
-
-    #             yield [
-    #                 "Analyzing video content...",
-    #                 "",
-    #                 "",
-    #                 gr.update(visible=False),
-    #                 gr.update(visible=True)
-    #             ]
-                
-    #             video_desc = detector.analyze_video_content(video)
-    #             formatted_desc = f"#Summary: {video_desc[:500] + '...' if len(video_desc) > 500 else video_desc}"
-                
-    #             # Update description as soon as it's available
-    #             yield [
-    #                 "Determining highlight types...",
-    #                 formatted_desc,
-    #                 "",
-    #                 gr.update(visible=False),
-    #                 gr.update(visible=True)
-    #             ]
-                
-    #             highlights = detector.determine_highlights(video_desc)
-    #             formatted_highlights = f"#Highlights to search for: {highlights[:500] + '...' if len(highlights) > 500 else highlights}"
-                
-    #             # Update highlights as soon as they're available
-    #             yield [
-    #                 "Detecting and extracting highlights...",
-    #                 formatted_desc,
-    #                 formatted_highlights,
-    #                 gr.update(visible=False),
-    #                 gr.update(visible=True)
-    #             ]
-
-    #             with tempfile.NamedTemporaryFile(suffix='.mp4', delete=False) as tmp_file:
-    #                 temp_output = tmp_file.name
-    #             detector.create_highlight_video(video, temp_output)
-                
-    #             yield [
-    #                 "Processing complete!",
-    #                 formatted_desc,
-    #                 formatted_highlights,
-    #                 gr.update(value=temp_output, visible=True),
-    #                 gr.update(visible=True)
-    #             ]
-
-    #         except Exception as e:
-    #             yield [
-    #                 f"Error processing video: {str(e)}",
-    #                 "",
-    #                 "",
-    #                 gr.update(visible=False),
-    #                 gr.update(visible=False)
-    #             ]
-
-    #     process_btn.click(
-    #         on_process,
-    #         inputs=[input_video],
-    #         outputs=[
-    #             status,
-    #             video_description,
-    #             highlight_types,
-    #             output_video,
-    #             analysis_accordion
-    #         ],
-    #         queue=True,
-    #     )
-
-    # return app
 
 if __name__ == "__main__":
     # Initialize CUDA

video_highlight_detector.py

@@ -318,7 +318,6 @@ class BatchedVideoHighlightDetector:
         batch_size=8,
         max_frames_per_segment=32,
         target_fps=1.0,
-        progress_callback=None
     ):
         self.model = model
         self.processor = processor
@@ -326,7 +325,6 @@ class BatchedVideoHighlightDetector:
         self.batch_size = batch_size
         self.max_frames_per_segment = max_frames_per_segment
         self.target_fps = target_fps
-        self.progress_callback = progress_callback
 
     def _extract_frames_batch(
         self,
@@ -498,10 +496,7 @@ class BatchedVideoHighlightDetector:
             for output in outputs
         ]
         
-        # Update progress if callback is provided
-        if self.progress_callback:
-            self.progress_callback(segments_processed + len(segments), total_segments)
-        
+
         # Check for "yes" in responses
         return ["yes" in response for response in responses]