Update app.py

app.py

@@ -257,8 +257,8 @@ def play_video(selected_video):
 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)
@@ -269,30 +269,32 @@ 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
 
-    ## Frame generator for real-time streaming
-    #def frame_generator():
-    #    for frame in prod_video:
-    #        yield frame # Stream frame-by-frame
+    # Frame generator for real-time streaming
+    def frame_generator():
+        for frame in prod_video:
+            yield frame # Stream frame-by-frame
             
-    return gesture_translation , prod_video#, frame_generator
+    return gesture_translation , frame_generator #prod_video
 
 with gr.Blocks() as demo:
     gr.Markdown("# Indian Sign Language Translation App")
     
     # Gesture recognition Tab
     with gr.Tab("Gesture recognition"):
-        with gr.Row(height=300, variant="panel", equal_height=False, show_progress=True):
+        with gr.Row(height=300, variant="panel"): # equal_height=False, 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")
             with gr.Column(scale=1, variant="panel"):
                 # Display the landmarked video
-                video_output = gr.Video(streaming=False, label="Landmarked Gesture")
-        with gr.Row(variant="panel", equal_height=False, show_progress=True):
-            # Submit the Video
-            video_button = gr.Button("Submit")
-            # Add a button or functionality to process the video
-            text_output = gr.Textbox(label="Translation in English")
+                video_output = gr.Video(streaming=True, label="Landmarked Gesture")
+        with gr.Row(variant="panel"): # equal_height=False, show_progress=True
+            with gr.Column(scale=1, variant="panel"):
+                # Submit the Video
+                video_button = gr.Button("Submit")
+            with gr.Column(scale=1, variant="panel"):
+                # Add a button or functionality to process the video
+                text_output = gr.Textbox(label="Translation in English")
     # Set up the interface
     video_button.click(translate_sign_language, inputs=video_input, outputs=[text_output, video_output])