feat: lang detector from file by api

main.py

@@ -59,12 +59,21 @@ async def health_check():
 @app.post("/detect-language")
 async def detect_language(file: UploadFile = File(...)):
     try:
-        # Read the audio file
-        contents = await file.read()
+        # Create uploads directory if it doesn't exist
+        os.makedirs("uploads", exist_ok=True)
         
-        # Use the language detector
+        # Save the uploaded file
+        file_path = os.path.join("uploads", file.filename)
+        with open(file_path, "wb") as buffer:
+            contents = await file.read()
+            buffer.write(contents)
+        
+        # Use the language detector with the saved file
         if language_detector:
-            detected_lang, confidence = language_detector.detect_language_from_bytes(contents)
+            detected_lang, confidence = language_detector.detect_language_from_file(file_path)
+            
+            # Clean up - remove the temporary file
+            os.remove(file_path)
             
             return JSONResponse({
                 "language": detected_lang,
@@ -79,6 +88,9 @@ async def detect_language(file: UploadFile = File(...)):
     except Exception as e:
         logger.error(f"Error in language detection: {e}")
         logger.error(f"Traceback: {traceback.format_exc()}")
+        # Clean up in case of error
+        if 'file_path' in locals() and os.path.exists(file_path):
+            os.remove(file_path)
         return JSONResponse(
             {"error": str(e)},
             status_code=500
@@ -133,177 +145,33 @@ async def websocket_endpoint(websocket: WebSocket):
                 logger.debug(f"Received audio chunk of size: {len(message)}")
                 await audio_processor.process_audio(message)
             except WebSocketDisconnect:
-                logger.warning("WebSocket disconnected.")
+                logger.info("WebSocket connection closed")
                 break
             except Exception as e:
-                logger.error(f"Error processing audio chunk: {e}")
+                logger.error(f"Error processing WebSocket message: {e}")
                 logger.error(f"Traceback: {traceback.format_exc()}")
                 break
 
-    except WebSocketDisconnect:
-        logger.warning("WebSocket disconnected during setup.")
     except Exception as e:
         logger.error(f"Error in WebSocket endpoint: {e}")
         logger.error(f"Traceback: {traceback.format_exc()}")
     finally:
+        if audio_processor:
+            await audio_processor.cleanup()
         if websocket_task:
             websocket_task.cancel()
             try:
                 await websocket_task
             except asyncio.CancelledError:
                 pass
-        if audio_processor:
-            await audio_processor.cleanup()
-        logger.info("WebSocket endpoint cleaned up.")
-
-def parse_args():
-    parser = argparse.ArgumentParser(description="Whisper FastAPI Online Server")
-    parser.add_argument(
-        "--host",
-        type=str,
-        default="localhost",
-        help="The host address to bind the server to.",
-    )
-    parser.add_argument(
-        "--port", type=int, default=8000, help="The port number to bind the server to."
-    )
-    parser.add_argument(
-        "--warmup-file",
-        type=str,
-        default=None,
-        dest="warmup_file",
-        help="""
-        The path to a speech audio wav file to warm up Whisper so that the very first chunk processing is fast.
-        If not set, uses https://github.com/ggerganov/whisper.cpp/raw/master/samples/jfk.wav.
-        If False, no warmup is performed.
-        """,
-    )
-
-    parser.add_argument(
-        "--confidence-validation",
-        action="store_true",
-        help="Accelerates validation of tokens using confidence scores. Transcription will be faster but punctuation might be less accurate.",
-    )
-
-    parser.add_argument(
-        "--diarization",
-        action="store_true",
-        default=False,
-        help="Enable speaker diarization.",
-    )
-
-    parser.add_argument(
-        "--no-transcription",
-        action="store_true",
-        help="Disable transcription to only see live diarization results.",
-    )
-    
-    parser.add_argument(
-        "--min-chunk-size",
-        type=float,
-        default=0.5,
-        help="Minimum audio chunk size in seconds. It waits up to this time to do processing. If the processing takes shorter time, it waits, otherwise it processes the whole segment that was received by this time.",
-    )
-    
-    parser.add_argument(
-        "--model",
-        type=str,
-        default="tiny",
-        help="Name size of the Whisper model to use (default: tiny). Suggested values: tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo. The model is automatically downloaded from the model hub if not present in model cache dir.",
-    )
-    
-    parser.add_argument(
-        "--model_cache_dir",
-        type=str,
-        default=None,
-        help="Overriding the default model cache dir where models downloaded from the hub are saved",
-    )
-    parser.add_argument(
-        "--model_dir",
-        type=str,
-        default=None,
-        help="Dir where Whisper model.bin and other files are saved. This option overrides --model and --model_cache_dir parameter.",
-    )
-    parser.add_argument(
-        "--lan",
-        "--language",
-        type=str,
-        default="en",
-        help="Source language code, e.g. en,de,cs, or 'auto' for language detection.",
-    )
-    parser.add_argument(
-        "--task",
-        type=str,
-        default="transcribe",
-        choices=["transcribe", "translate"],
-        help="Transcribe or translate.",
-    )
-    parser.add_argument(
-        "--backend",
-        type=str,
-        default="faster-whisper",
-        choices=["faster-whisper", "whisper_timestamped", "mlx-whisper", "openai-api"],
-        help="Load only this backend for Whisper processing.",
-    )
-    parser.add_argument(
-        "--vac",
-        action="store_true",
-        default=False,
-        help="Use VAC = voice activity controller. Recommended. Requires torch.",
-    )
-    parser.add_argument(
-        "--vac-chunk-size", type=float, default=0.04, help="VAC sample size in seconds."
-    )
-    parser.add_argument(
-        "--no-vad",
-        action="store_true",
-        default=False,
-        help="Disable VAD = voice activity detection. Not recommended.",
-    )
-    parser.add_argument(
-        "--buffer_trimming",
-        type=str,
-        default="sentence",
-        choices=["sentence", "segment"],
-        help="Buffer trimming strategy.",
-    )
-    parser.add_argument(
-        "--buffer_trimming_sec",
-        type=float,
-        default=1.0,
-        help="Buffer trimming length in seconds.",
-    )
-    parser.add_argument(
-        "-l",
-        "--log-level",
-        type=str,
-        default="INFO",
-        choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
-        help="Set the logging level.",
-    )
 
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--host", type=str, default="0.0.0.0", help="Host to run the server on")
+    parser.add_argument("--port", type=int, default=8000, help="Port to run the server on")
+    parser.add_argument("--model", type=str, default="base", help="Whisper model to use")
+    parser.add_argument("--backend", type=str, default="faster-whisper", help="Backend to use")
+    parser.add_argument("--task", type=str, default="transcribe", help="Task to perform")
     args = parser.parse_args()
-    
-    args.transcription = not args.no_transcription
-    args.vad = not args.no_vad    
-    delattr(args, 'no_transcription')
-    delattr(args, 'no_vad')
-    
-    return args
-
-def main():
-    args = parse_args()
-    
-    # Initialize WhisperLiveKit with parsed arguments
-    kit = WhisperLiveKit(args=args)
-    
-    # Start the server
-    uvicorn.run(
-        "main:app",
-        host=args.host,
-        port=args.port,
-        log_level=args.log_level.lower()
-    )
 
-if __name__ == "__main__":
-    main() 
+    uvicorn.run(app, host=args.host, port=args.port)