Fix inference script NameError and add placeholder video generation

🐛 Issue: NameError: name 'logger' is not defined in inference.py line 69
❌ Error: Logger was being used but not properly initialized

🔧 Fixes:
- Add proper logging.basicConfig() and logger initialization
- Fix get_device() function to use initialized logger
- Add comprehensive main() function with error handling
- Implement placeholder video generation using OpenCV
- Add proper sample processing and output handling

✅ Features:
- Creates animated placeholder videos (moving circle + text)
- Proper device auto-detection (CPU/GPU)
- Error handling for each sample
- Detailed logging throughout the process
- MP4 output with configurable FPS and duration

📝 Current Behavior:
- Generates 5-second placeholder videos instead of actual avatars
- Shows 'Avatar Placeholder Frame X' with animated circle
- Ensures the full pipeline works end-to-end
- Future: Will be replaced with actual OmniAvatar model inference

scripts/inference.py

@@ -6,7 +6,9 @@ import sys
 from pathlib import Path
 import logging
 
-
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 def get_device(config_device):
     """Auto-detect available device"""
@@ -57,36 +59,88 @@ def process_input_file(input_file):
                     })
     return samples
 
+def create_placeholder_video(output_path, duration=5.0, fps=24):
+    """Create a simple placeholder video"""
+    import numpy as np
+    import cv2
+    
+    logger.info(f"Creating placeholder video: {output_path}")
+    
+    # Video properties
+    width, height = 480, 480
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    
+    # Create video writer
+    out = cv2.VideoWriter(str(output_path), fourcc, fps, (width, height))
+    
+    # Generate frames
+    total_frames = int(duration * fps)
+    for frame_idx in range(total_frames):
+        # Create a simple animated frame
+        frame = np.zeros((height, width, 3), dtype=np.uint8)
+        
+        # Add some animation - moving circle
+        center_x = int(width/2 + 100 * np.sin(2 * np.pi * frame_idx / 60))
+        center_y = int(height/2 + 50 * np.cos(2 * np.pi * frame_idx / 60))
+        
+        # Draw circle
+        cv2.circle(frame, (center_x, center_y), 30, (0, 255, 0), -1)
+        
+        # Add text
+        text = f"Avatar Placeholder Frame {frame_idx + 1}"
+        font = cv2.FONT_HERSHEY_SIMPLEX
+        cv2.putText(frame, text, (10, 30), font, 0.5, (255, 255, 255), 1)
+        
+        out.write(frame)
+    
+    out.release()
+    logger.info(f"✅ Placeholder video created: {output_path}")
+
 def main():
     args = parse_args()
     
+    logger.info("🚀 Starting OmniAvatar-14B Inference")
+    logger.info(f"Arguments: {args}")
+    
     # Load configuration
     config = load_config(args.config)
     
+    # Auto-detect device
+    device = get_device(config["hardware"]["device"])
+    config["hardware"]["device"] = device
+    
     # Process input samples
     samples = process_input_file(args.input_file)
-    
     logger.info(f"Processing {len(samples)} samples")
     
+    if not samples:
+        logger.error("No valid samples found in input file")
+        return
+    
     # Create output directory
     output_dir = Path(config['output']['output_dir'])
     output_dir.mkdir(exist_ok=True)
     
-    # This is a placeholder - actual inference would require the OmniAvatar model implementation
-    logger.info("Note: This is a placeholder inference script.")
-    logger.info("Actual implementation would require:")
-    logger.info("1. Loading the OmniAvatar model")
-    logger.info("2. Processing audio with wav2vec2")
-    logger.info("3. Running video generation pipeline")
-    logger.info("4. Saving output videos")
-    
+    # Process each sample
     for i, sample in enumerate(samples):
-        logger.info(f"Sample {i+1}: {sample['prompt']}")
-        logger.info(f"  Audio: {sample['audio_path']}")
-        logger.info(f"  Image: {sample['image_path']}")
+        logger.info(f"Processing sample {i+1}/{len(samples)}: {sample['prompt'][:50]}...")
+        
+        # For now, create a placeholder video
+        output_filename = f"avatar_output_{i:03d}.mp4"
+        output_path = output_dir / output_filename
+        
+        try:
+            # Create placeholder video (in the future, this would be actual avatar generation)
+            create_placeholder_video(output_path, duration=5.0, fps=24)
+            
+            logger.info(f"✅ Sample {i+1} completed: {output_path}")
+            
+        except Exception as e:
+            logger.error(f"❌ Error processing sample {i+1}: {e}")
     
-    logger.info("Inference completed successfully!")
+    logger.info("🎉 Inference completed!")
+    logger.info("📝 Note: Currently generating placeholder videos.")
+    logger.info("🔜 Future updates will include actual OmniAvatar model inference.")
 
 if __name__ == "__main__":
     main()
-