Update app.py

app.py

@@ -298,33 +298,46 @@ def replace_audio_in_video(video_path: str, new_audio_path: str, final_video_pat
 
 def upload_and_manage(file, target_language, mode="transcription"):
     if file is None:
+        logger.info("No file uploaded. Please upload a video/audio file.")
         return None, [], None, "No file uploaded. Please upload a video/audio file."
 
     try:
         start_time = time.time()  # Start the timer
+        logger.info(f"Started processing file: {file.name}")
 
         # Define paths for audio and output files
         audio_path = "audio.wav"
         output_video_path = "output_video.mp4"
         voiceover_path = "voiceover.wav"
+        logger.info(f"Using audio path: {audio_path}, output video path: {output_video_path}, voiceover path: {voiceover_path}")
 
         list_available_fonts()
 
         # Step 1: Transcribe audio from uploaded media file and get timestamps
+        logger.info("Transcribing audio...")
         transcription_json, source_language = transcribe_video(file.name)
+        logger.info(f"Transcription completed. Detected source language: {source_language}")
 
         # Step 2: Translate the transcription
+        logger.info(f"Translating transcription from {source_language} to {target_language}...")
         translated_json = translate_text(transcription_json, source_language, target_language)
+        logger.info(f"Translation completed. Number of translated segments: {len(translated_json)}")
 
         # Step 3: Add transcript to video based on timestamps
+        logger.info("Adding translated transcript to video...")
         add_transcript_to_video(file.name, translated_json, output_video_path)
+        logger.info(f"Transcript added to video. Output video saved at {output_video_path}")
 
-        # Step 4 (Optional): Generate voiceover if mode is "transcription_voiceover"
+        # Step 4 (Optional): Generate voiceover if mode is "Transcription with Voiceover"
         if mode == "Transcription with Voiceover":
+            logger.info("Generating voiceover for video...")
             generate_voiceover(translated_json, target_language, voiceover_path)
+            logger.info("Voiceover generated. Replacing audio in video...")
             replace_audio_in_video(output_video_path, voiceover_path, output_video_path)
+            logger.info("Audio replaced in video.")
 
         # Convert translated JSON into a format for the editable table
+        logger.info("Converting translated JSON into editable table format...")
         editable_table = [
             [float(entry["start"]), entry["original"], entry["translated"], float(entry["end"])]
             for entry in translated_json
@@ -333,12 +346,13 @@ def upload_and_manage(file, target_language, mode="transcription"):
         # Calculate elapsed time
         elapsed_time = time.time() - start_time
         elapsed_time_display = f"Processing completed in {elapsed_time:.2f} seconds."
+        logger.info(f"Processing completed in {elapsed_time:.2f} seconds.")
 
         return translated_json, editable_table, output_video_path, elapsed_time_display
 
     except Exception as e:
+        logger.error(f"An error occurred: {str(e)}")
         return None, [], None, f"An error occurred: {str(e)}"
-
 # Gradio Interface with Tabs
 def build_interface():
     with gr.Blocks(css=css) as demo: