add whisperx support

meetus/transcript_merger.py

@@ -45,14 +45,15 @@ class TranscriptMerger:
             with open(path, 'r', encoding='utf-8') as f:
                 data = json.load(f)
 
-            # Handle different Whisper output formats
+            # Handle different Whisper/WhisperX output formats
             segments = []
             if isinstance(data, dict) and 'segments' in data:
-                # Standard Whisper JSON format
+                # Standard Whisper/WhisperX JSON format
                 segments = [
                     {
                         'timestamp': seg.get('start', 0),
                         'text': seg['text'].strip(),
+                        'speaker': seg.get('speaker'),  # WhisperX diarization
                         'type': 'audio'
                     }
                     for seg in data['segments']
@@ -63,6 +64,7 @@ class TranscriptMerger:
                     {
                         'timestamp': seg.get('start', seg.get('timestamp', 0)),
                         'text': seg['text'].strip(),
+                        'speaker': seg.get('speaker'),  # WhisperX diarization
                         'type': 'audio'
                     }
                     for seg in data
@@ -207,35 +209,28 @@ class TranscriptMerger:
         lines = []
         lines.append("=" * 80)
         lines.append("ENHANCED MEETING TRANSCRIPT")
-        if self.embed_images:
-            lines.append("Audio transcript + Embedded frame images (base64)")
-        else:
-            lines.append("Audio transcript + Screen content")
+        lines.append("Audio transcript + Screen frames")
         lines.append("=" * 80)
         lines.append("")
 
-        total_image_bytes = 0
-
         for seg in segments:
             timestamp = self._format_timestamp(seg['timestamp'])
 
             if seg['type'] == 'audio':
-                lines.append(f"[{timestamp}] SPEAKER:")
+                speaker = seg.get('speaker', 'SPEAKER')
+                lines.append(f"[{timestamp}] {speaker}:")
                 lines.append(f"  {seg['text']}")
                 lines.append("")
 
             else:  # screen
                 lines.append(f"[{timestamp}] SCREEN CONTENT:")
 
-                # Embed image if requested
-                if self.embed_images and 'frame_path' in seg:
-                    b64_img, img_size = self._encode_image_base64(seg['frame_path'])
-                    total_image_bytes += img_size
-
-                    if b64_img:
-                        lines.append(f"  IMAGE (base64, {img_size // 1024}KB):")
-                        lines.append(f"  <image>data:image/jpeg;base64,{b64_img}</image>")
-                        lines.append("")
+                # Show frame path if available
+                if 'frame_path' in seg:
+                    # Get just the filename relative to the enhanced transcript
+                    frame_path = Path(seg['frame_path'])
+                    relative_path = f"frames/{frame_path.name}"
+                    lines.append(f"  Frame: {relative_path}")
 
                 # Include text content if available (fallback or additional context)
                 if 'text' in seg and seg['text'].strip():
@@ -245,12 +240,6 @@ class TranscriptMerger:
 
                 lines.append("")
 
-        if self.embed_images and total_image_bytes > 0:
-            total_mb = total_image_bytes / (1024 * 1024)
-            lines.append("")
-            lines.append(f"Total embedded images size: {total_mb:.2f} MB")
-            logger.info(f"Embedded {len([s for s in segments if s['type'] == 'screen'])} images, total size: {total_mb:.2f} MB")
-
         return "\n".join(lines)
 
     def _format_compact(self, segments: List[Dict]) -> str:
@@ -259,7 +248,10 @@ class TranscriptMerger:
 
         for seg in segments:
             timestamp = self._format_timestamp(seg['timestamp'])
-            prefix = "SPEAKER" if seg['type'] == 'audio' else "SCREEN"
+            if seg['type'] == 'audio':
+                prefix = seg.get('speaker', 'SPEAKER')
+            else:
+                prefix = "SCREEN"
             text = seg['text'].replace('\n', ' ')[:200]  # Truncate long screen text
             lines.append(f"[{timestamp}] {prefix}: {text}")
 

meetus/workflow.py

@@ -184,10 +184,10 @@ class ProcessingWorkflow:
         logger.info("STEP 0: Running Whisper Transcription")
         logger.info("=" * 80)
 
-        # Check if whisper is installed
-        if not shutil.which("whisper"):
-            logger.error("Whisper is not installed. Install it with: pip install openai-whisper")
-            raise RuntimeError("Whisper not installed")
+        # Check if whisperx is installed
+        if not shutil.which("whisperx"):
+            logger.error("WhisperX is not installed. Install it with: pip install whisperx")
+            raise RuntimeError("WhisperX not installed")
 
         # Unload Ollama model to free GPU memory for Whisper (if using vision)
         if self.config.use_vision:
@@ -199,16 +199,17 @@ class ProcessingWorkflow:
             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(f"Running WhisperX transcription with diarization (model: {self.config.whisper_model})...")
         logger.info("This may take a few minutes depending on video length...")
 
-        # Run whisper command
+        # Run whisperx command with diarization
         cmd = [
-            "whisper",
+            "whisperx",
             str(self.config.video_path),
             "--model", self.config.whisper_model,
             "--output_format", "json",
-            "--output_dir", str(self.output_mgr.output_dir)
+            "--output_dir", str(self.output_mgr.output_dir),
+            "--diarize",
         ]
 
         try: