Update app.py

app.py

@@ -253,16 +253,12 @@ def list_videos():
 def play_video(selected_video):
     return os.path.join(data_path, selected_video) if selected_video else None
 
-## Function to refresh dropdown options
-#def refresh_dropdown():
-#    return gr.Dropdown.update(choices=list_videos())
-
 # Main Function for tab - Gesture recognition
 def translate_sign_language(gesture):
     # Create Dataset
     prod_ds = dataset_prod_obj.create_dataset(gesture)
-    #prod_video = tensor_to_video(prod_ds)
-    prod_video = np.random.randint(0, 255, (32, 225, 225, 3), dtype=np.uint8)
+    prod_video = tensor_to_video(prod_ds)
+    #prod_video = np.random.randint(0, 255, (32, 225, 225, 3), dtype=np.uint8)
     
     # Run ML Model
     predicted_prod_label = prod_function(model_pretrained, prod_ds)
@@ -272,23 +268,29 @@ def translate_sign_language(gesture):
     
     idx_to_label = model_pretrained.config.id2label
     gesture_translation = idx_to_label[predicted_prod_label.cpu().numpy().item()] # Convert to a scalar
-    
-    return gesture_translation , prod_video
+
+    # Frame generator for real-time streaming
+    def frame_generator():
+        for frame in prod_video:
+            yield frame # Stream frame-by-frame
+            
+    return gesture_translation , frame_generator
 
 with gr.Blocks() as demo:
     gr.Markdown("# Indian Sign Language Translation App")
     
     # Gesture recognition Tab
     with gr.Tab("Gesture recognition"):
-        with gr.Row():
-            with gr.Column(scale=2, min_width=300):
+        with gr.Row(height=300, variant="panel", equal_height=True, show_progress=True):
+            with gr.Column(scale=1, variant="panel"):
                 # Add webcam input for sign language video capture
                 video_input = gr.Video(format="mp4", label="Gesture")
                 # Submit the Video
                 video_button = gr.Button("Submit")
-            # Display the landmarked video
-            video_output = gr.Video(streaming=True, label="Landmarked Gesture")
-        with gr.Row():
+            with gr.Column(scale=1, variant="panel"):
+                # Display the landmarked video
+                video_output = gr.Video(streaming=True, label="Landmarked Gesture")
+        with gr.Row(height=300, variant="panel", equal_height=True, show_progress=True):
             # Add a button or functionality to process the video
             test_output = gr.Textbox(label="Translation in English")
     # Set up the interface
@@ -296,10 +298,12 @@ with gr.Blocks() as demo:
     
     # Indian Sign Language gesture reference tab
     with gr.Tab("Indian Sign Language gesture reference"):
-        with gr.Row():
-            video_dropdown = gr.Dropdown(choices=list_videos(), label="ISL gestures", info="More gestures comming soon!")
-            search_button = gr.Button("Search Gesture")
-            search_output = gr.Video(streaming=True, label="ISL gestures Video")
+        with gr.Row(height=300, variant="panel", equal_height=True, show_progress=True):
+            with gr.Column(scale=1, variant="panel"):
+                video_dropdown = gr.Dropdown(choices=list_videos(), label="ISL gestures", info="More gestures comming soon!")
+                search_button = gr.Button("Search Gesture")
+            with gr.Column(scale=1, variant="panel"):
+                search_output = gr.Video(streaming=False, label="ISL gestures Video")
     # Set up the interface
     search_button.click(play_video, inputs=video_dropdown, outputs=search_output)