Integrated speech transcription

src/__init__.py

@@ -1,19 +0,0 @@
-"""
-Created By: ishwor subedi
-Date: 2024-07-31
-"""
-
-import logging.config
-import yaml
-import os
-
-if os.path.exists("logs"):
-    pass
-else:
-    os.makedirs("logs")
-
-log_config_path = os.path.join(os.getcwd(), "logging_config.yaml")
-with open(log_config_path, 'r') as file:
-    config = yaml.safe_load(file.read())
-
-logging.config.dictConfig(config)

src/api/speech_api.py

@@ -10,7 +10,6 @@ from fastapi import UploadFile, HTTPException, status
 from src.models.models import TextToSpeechRequest
 from fastapi.routing import APIRouter
 from src.pipeline.speech_transcription_pipeline import SpeechTranscriptionPipeline
-from src import logging
 
 speech_translator_router = APIRouter(tags=["SpeechTranscription"])
 pipeline = SpeechTranscriptionPipeline()
@@ -85,19 +84,14 @@ pipeline = SpeechTranscriptionPipeline()
     """
 )
 async def text_to_speech(request: TextToSpeechRequest):
-    logging.info(f"Text to speech request received")
     try:
         audio_bytes = pipeline.text_to_speech(request.text, request.lang, request.tld)
         if not audio_bytes:
-            logging.error(f"Audio generation failed.")
             raise ValueError("Audio generation failed.")
-        logging.info(f"Text to speech request processed successfully")
         return JSONResponse(content={"audio": audio_bytes, "status_code": status.HTTP_200_OK}, status_code=200)
     except ValueError as ve:
-        logging.error(f"Error processing text to speech request: {str(ve)}")
         raise HTTPException(status_code=400, detail=str(ve))
     except Exception as e:
-        logging.error(f"Internal Server Error: {str(e)}")
         raise HTTPException(status_code=500, detail="Internal Server Error")
 
 
@@ -147,14 +141,11 @@ async def text_to_speech(request: TextToSpeechRequest):
     """
 )
 async def speech_to_text(audio: UploadFile, lang: str = Form(...)):
-    logging.info(f"Speech to text request received")
     try:
         audio_bytes = await audio.read()
         if not audio_bytes:
-            logging.error(f"Empty audio file")
             raise ValueError("Empty audio file")
     except Exception as e:
-        logging.error(f"Invalid audio file {e}")
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail="Invalid audio file"
@@ -164,32 +155,27 @@ async def speech_to_text(audio: UploadFile, lang: str = Form(...)):
         with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio_file:
             temp_audio_file.write(audio_bytes)
             temp_audio_file_path = temp_audio_file.name
-            logging.info(f"Temporary audio file created at {temp_audio_file_path}")
     except Exception as e:
-        logging.error(f"Could not process audio file{e}")
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail="Could not process audio file"
         )
 
     try:
-        logging.info(f"Transcribing audio to text")
         transcript = pipeline.speech_to_text(temp_audio_file_path, lang)
     except FileNotFoundError as fnfe:
-        logging.error(f"Temporary file not found{fnfel}")
         raise HTTPException(
             status_code=status.HTTP_404_NOT_FOUND,
             detail="Temporary file not found"
         )
     except Exception as e:
-        logging.error(f"Error processing speech-to-text: {str(e)}")
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail="Error processing speech-to-text"
         )
     finally:
-        logging.info(f"Cleaning up temporary audio file")
         if os.path.exists(temp_audio_file_path):
             os.remove(temp_audio_file_path)
 
     return JSONResponse(content={"transcript": transcript, "status_code": status.HTTP_200_OK}, status_code=200)
+