VideoLingo icon indicating copy to clipboard operation
VideoLingo copied to clipboard

硅基流动 sf_cosyvoice2 请求频繁返回400 错误

Open silendir opened this issue 7 months ago • 0 comments

使用 硅基流动 sf_cosyvoice2 一直很稳定, 直到上次更新Master分支, 就经常报400请求错误, 最终merge音频的时候经常提示音频包超过5mb, 尝试多次均不能完成特定项目, 而且任何视频都会屡次报400返回错误, 在 config.yaml中 更改max_length: 50 和 max_split_length: 18 也同样如此

Traceback (most recent call last): File "/Volumes/闪迪2T/VideoLingo/videolingo_venv/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 88, in exec_func_with_error_handling result = func() ^^^^^^ File "/Volumes/闪迪2T/VideoLingo/videolingo_venv/lib/python3.11/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 590, in code_to_exec exec(code, module.dict) File "/Volumes/闪迪2T/VideoLingo_粗口/st.py", line 124, in main() File "/Volumes/闪迪2T/VideoLingo_粗口/st.py", line 121, in main audio_processing_section() File "/Volumes/闪迪2T/VideoLingo_粗口/st.py", line 79, in audio_processing_section process_audio() File "/Volumes/闪迪2T/VideoLingo_粗口/st.py", line 99, in process_audio _10_gen_audio.gen_audio() File "/Volumes/闪迪2T/VideoLingo_粗口/core/_10_gen_audio.py", line 222, in gen_audio tasks_df = generate_tts_audio(tasks_df) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/闪迪2T/VideoLingo_粗口/core/_10_gen_audio.py", line 113, in generate_tts_audio raise e File "/Volumes/闪迪2T/VideoLingo_粗口/core/_10_gen_audio.py", line 108, in generate_tts_audio number, real_dur = future.result() ^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/concurrent/futures/_base.py", line 449, in result return self.__get_result() ^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/concurrent/futures/_base.py", line 401, in __get_result raise self._exception File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/concurrent/futures/thread.py", line 58, in run result = self.fn(*self.args, **self.kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Volumes/闪迪2T/VideoLingo_粗口/core/_10_gen_audio.py", line 72, in process_row tts_main(line, temp_file, number, tasks_df) File "/Volumes/闪迪2T/VideoLingo_粗口/core/tts_backend/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: Error code: 413 - {'code': 20045, 'message': 'Too large audios. Total size should less than 5MB.', 'data': None}

silendir avatar Jun 26 '25 11:06 silendir