#1796 TaskCfg(cache_folder='D:/pyvideotrans/tmp9168/2545e31338', target_dir='E:/admin/Downloads/Video/_video_out/4k2.com@boko-

3.112* Posted at: 3 days ago 👁19

语音识别阶段出错:[openai-whisper(本地)] 运行时错误:Traceback (most recent call last):
File "videotrans\process\_overall.py", line 44, in run
File "whisper\__init__.py", line 137, in load_model
File "whisper\__init__.py", line 91, in _download
RuntimeError: Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.
:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\trans_create.py", line 354, in recogn
File "videotrans\recognition\__init__.py", line 236, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_overall.py", line 193, in _exec
RuntimeError: Traceback (most recent call last):
File "videotrans\process\_overall.py", line 44, in run
File "whisper\__init__.py", line 137, in load_model
File "whisper\__init__.py", line 91, in _download
RuntimeError: Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.

TaskCfg(cache_folder='D:/pyvideotrans/tmp9168/2545e31338', target_dir='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028', remove_noise=False, is_separate=False, detect_language='ja', subtitle_language=None, source_language='日语', target_language='简体中文', source_language_code='ja', target_language_code='zh-cn', source_sub='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028/ja.srt', target_sub='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028/zh-cn.srt', source_wav='D:/pyvideotrans/tmp9168/2545e31338/ja.wav', source_wav_output='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028/ja.m4a', target_wav='D:/pyvideotrans/tmp9168/2545e31338/target.wav', target_wav_output='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028/zh-cn.m4a', subtitles='', novoice_mp4='D:/pyvideotrans/tmp9168/2545e31338/novoice.mp4', noextname='4k2.com@boko-028', shibie_audio=None, targetdir_mp4='E:/admin/Downloads/Video/_video_out/4k2.com@boko-028/[email protected]4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='tiqu', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=1, model_name='large-v3-turbo', split_type=0, voice_autorate=False, video_autorate=False, cuda=False, name='E:/admin/Downloads/Video/[email protected]4', basename='[email protected]4', ext='mp4', dirname='E:/admin/Downloads/Video', shound_del_name=None, uuid='2545e31338', remove_silent_mid=False, align_sub_audio=False, enable_diariz=False, nums_diariz=0, auto_fix=True)


=
system:Windows-10-10.0.26100-SP0
version:v3.86
frozen:True
language:zh
root_dir:D:/pyvideotrans

1 Replies

该错误表明您选择的 openai-whisper(本地) 模型文件在下载或缓存过程中损坏,导致 SHA256 校验和不匹配。请按以下步骤解决:

  1. 清理损坏的模型缓存

    • 打开文件资源管理器,进入路径 C:\Users\[你的用户名]\.cache\whisper
    • 删除该目录下的所有文件(或至少删除 large-v3-turbo.pt 文件)。
    • 如果找不到 .cache 文件夹,请确保在文件资源管理器中开启了“显示隐藏的项目”。
  2. 重新下载模型

    • 返回 pyVideoTrans 主界面,确保网络连接正常(可能需要代理)。
    • 再次尝试运行语音识别任务,软件会自动重新下载模型。
  3. (备用方案)更换识别模型

    • 如果上述步骤无效或下载缓慢,建议在主界面第2行的“语音识别”处,将模型更换为 faster-whisper(本地)
    • faster-whisper 是更推荐的选择,速度更快,且模型文件独立存储,不易出现此问题。

如果问题依旧,请检查网络环境或防火墙/杀毒软件是否阻止了模型文件的正常下载。

Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Donate: https://ko-fi.com/jianchang512

Trending Questions