clean up code

app/parsers/audio_parser.py

@@ -0,0 +1,62 @@
+from pathlib import Path
+from typing import Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+class AudioParser:
+    def __init__(self, whisper_model: str = 'base'):
+        self.supported_formats = {'.mp3', '.wav', '.flac', '.m4a', '.ogg', '.wma', '.aac'}
+        self.whisper_model = whisper_model
+
+    def parse(self, file_path: Path) -> Dict:
+        if file_path.suffix.lower() not in self.supported_formats:
+            return {'error': f'Unsupported format: {file_path.suffix}'}
+
+        try:
+            return self._transcribe_with_whisper(file_path)
+        except Exception as e:
+            logger.error(f'Audio parse failed for {file_path}: {e}')
+            return {'error': str(e), 'text': ''}
+
+    def _transcribe_with_whisper(self, file_path: Path) -> Dict:
+        try:
+            import whisper
+
+            model = whisper.load_model(self.whisper_model)
+            result = model.transcribe(str(file_path))
+
+            return {
+                'text': result['text'].strip(),
+                'quality': 'good',
+                'method': f'whisper-{self.whisper_model}',
+                'language': result.get('language', 'unknown'),
+                'segments': len(result.get('segments', [])),
+                'metadata': {
+                    'duration': result.get('duration'),
+                    'language': result.get('language')
+                }
+            }
+        except ImportError:
+            logger.warning('Whisper not installed')
+            return {'error': 'Whisper not installed', 'text': '', 'needs': 'pip install openai-whisper'}
+        except Exception as e:
+            return {'error': str(e), 'text': ''}
+
+    def extract_metadata(self, file_path: Path) -> Dict:
+        try:
+            import mutagen
+            audio = mutagen.File(str(file_path))
+            if audio is None:
+                return {'error': 'Could not read audio file'}
+
+            return {
+                'duration': audio.info.length if hasattr(audio.info, 'length') else None,
+                'bitrate': audio.info.bitrate if hasattr(audio.info, 'bitrate') else None,
+                'sample_rate': audio.info.sample_rate if hasattr(audio.info, 'sample_rate') else None,
+                'channels': audio.info.channels if hasattr(audio.info, 'channels') else None
+            }
+        except ImportError:
+            return {'error': 'mutagen not installed', 'needs': 'pip install mutagen'}
+        except Exception as e:
+            return {'error': str(e)}