GPT-SoVits Dubbing: Exception: Failed to generate audio after 3 attempts: [Errno 2] No such file or directory: 'config.yaml'

I am using the pre-trained Huanyuv2 model for the Gpt-SoVits dubbing, but turns out it doesn't works. Below is the error returned.

2025-03-03 00:35:58.480 Uncaught app exception
Traceback (most recent call last):
  File "C:\Users\Administrator\VideoLingo\core\all_tts_functions\tts_main.py", line 49, in tts_main
    correct_text = ask_gpt(get_correct_text_prompt(text),log_title='tts_correct_text')
  File "C:\Users\Administrator\VideoLingo\core\ask_gpt.py", line 47, in ask_gpt
    api_set = load_key("api")
  File "C:\Users\Administrator\VideoLingo\core\config_utils.py", line 16, in load_key
    with open(CONFIG_PATH, 'r', encoding='utf-8') as file:
FileNotFoundError: [Errno 2] No such file or directory: 'config.yaml'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\exec_code.py", line 88, in exec_func_with_error_handling
    result = func()
  File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 590, in code_to_exec
    exec(code, module.__dict__)
  File "C:\Users\Administrator\VideoLingo\st.py", line 124, in <module>
    main()
  File "C:\Users\Administrator\VideoLingo\st.py", line 121, in main
    audio_processing_section()
  File "C:\Users\Administrator\VideoLingo\st.py", line 79, in audio_processing_section
    process_audio()
  File "C:\Users\Administrator\VideoLingo\st.py", line 99, in process_audio
    step10_gen_audio.gen_audio()
  File "C:\Users\Administrator\VideoLingo\core\step10_gen_audio.py", line 228, in gen_audio
    tasks_df = generate_tts_audio(tasks_df)
  File "C:\Users\Administrator\VideoLingo\core\step10_gen_audio.py", line 99, in generate_tts_audio
    raise e
  File "C:\Users\Administrator\VideoLingo\core\step10_gen_audio.py", line 94, in generate_tts_audio
    number, real_dur = process_row(row, tasks_df)
  File "C:\Users\Administrator\VideoLingo\core\step10_gen_audio.py", line 78, in process_row
    tts_main(line, temp_file, number, tasks_df)
  File "C:\Users\Administrator\VideoLingo\core\all_tts_functions\tts_main.py", line 84, in tts_main
    raise Exception(f"Failed to generate audio after {max_retries} attempts: {str(e)}")
Exception: Failed to generate audio after 3 attempts: [Errno 2] No such file or directory: 'config.yaml'

Interestingly, after I press the "Start Audio Processing" button again. The error became

MediaFileStorageError: Error opening 'docs/logo.png'
Traceback:
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\exec_code.py", line 88, in exec_func_with_error_handling
    result = func()
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 590, in code_to_exec
    exec(code, module.__dict__)
File "C:\Users\Administrator\VideoLingo\st.py", line 124, in <module>
    main()
File "C:\Users\Administrator\VideoLingo\st.py", line 111, in main
    st.image("docs/logo.png", use_column_width=True)
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\metrics_util.py", line 410, in wrapped_func
    result = non_optional_func(*args, **kwargs)
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\elements\image.py", line 162, in image
    marshall_images(
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\elements\image.py", line 546, in marshall_images
    proto_img.url = image_to_url(
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\elements\image.py", line 397, in image_to_url
    url = runtime.get_instance().media_file_mgr.add(image, mimetype, image_id)
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\media_file_manager.py", line 226, in add
    file_id = self._storage.load_and_get_id(
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\memory_media_file_storage.py", line 115, in load_and_get_id
    file_data = self._read_file(path_or_data)
File "C:\Users\Administrator\.conda\envs\videolingo\lib\site-packages\streamlit\runtime\memory_media_file_storage.py", line 167, in _read_file
    raise MediaFileStorageError(f"Error opening '{filename}'") from ex

Start by reading core/config_utils.py, core/all_tts_functions/tts_main.py, and st.py, especially the config.yaml and docs/logo.png path usage shown in the traceback. Reproduce the Windows launch and audio-processing flow, then verify that both files resolve correctly and the Start Audio Processing action completes without either exception.