take turns using the GPU

meetus/workflow.py

@@ -158,6 +158,16 @@ class ProcessingWorkflow:
             logger.error("Whisper is not installed. Install it with: pip install openai-whisper")
             raise RuntimeError("Whisper not installed")
 
+        # Unload Ollama model to free GPU memory for Whisper (if using vision)
+        if self.config.use_vision:
+            logger.info("Freeing GPU memory for Whisper...")
+            try:
+                subprocess.run(["ollama", "stop", self.config.vision_model],
+                             capture_output=True, check=False)
+                logger.info("✓ Ollama model unloaded")
+            except Exception as e:
+                logger.warning(f"Could not unload Ollama model: {e}")
+
         logger.info(f"Running Whisper transcription (model: {self.config.whisper_model})...")
         logger.info("This may take a few minutes depending on video length...")
 
@@ -224,6 +234,7 @@ class ProcessingWorkflow:
     def _run_vision_analysis(self, frames_info):
         """Run vision analysis on frames."""
         logger.info("Step 2: Running vision analysis on extracted frames...")
+        logger.info(f"Loading vision model {self.config.vision_model} to GPU...")
 
         try:
             vision = VisionProcessor(model=self.config.vision_model)