#6324 帮看一下图里的报错是什么原因

216.236**8 Posted at: 1 month ago

帮看一下图里的报错是什么原因

3 Replies

#1 DeepSeek reply at 1 month ago

暂无法确定具体原因，因为图片内容无法直接查看。

请提供软件安装目录下 logs/ 文件夹中最新的日志文件内容（复制底部约30行报错信息），以及软件左上角的版本号，以便进一步分析。

#2 216.236**8 reply at 1 month ago

Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.:Traceback (most recent call last):
File "videotrans\process\stt_openai.py", line 52, in openai_whisper
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\only_one.py", line 62, in run
File "videotrans\task\_stage_recogn.py", line 62, in recogn
File "videotrans\recognition\__init__.py", line 206, in run
File "videotrans\recognition\_base.py", line 92, in run
File "videotrans\recognition\_whisper.py", line 39, in _exec
File "videotrans\recognition\_whisper.py", line 89, in _openai
File "videotrans\configure\base.py", line 267, in _new_process
videotrans.configure.excepts.VideoTransError: Model has been downloaded but the SHA256 checksum does not not match. Please retry loading the model.:Traceback (most recent call last):
File "videotrans\process\stt_openai.py", line 52, in openai_whisper
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.

cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频单视频模式
原始输入文件名: E:/日常搬砖/Youtube视频资源/Why China Is Building Ships in the Desert.mp4,
输出结果保存到文件夹: E:/日常搬砖/上架视频/Why China Is Building Ships in the Desert-mp4,
临时文件夹: E:/BaiduNetdisk

/win-pyvideotrans-v4.08-0802/tmp/7880/a1103fc222
已选清理已存在
已启用CUDA加速
未选降噪
语音识别:openai-whisper(内置), model_name: large-v3, 发音语言: 英语, 断句方式:默认断句
翻译渠道:Google(免费),原始语言:英语,目标语言:简体中文, 已选发送完整字幕
配音渠道:Edge-TTS(免费), 角色:Yunjian(Male/CN), 配音语言:简体中文, 未选二次语音识别
音量:+0%, 语速:+0%, 已选音频加速, 未选视频慢速
字幕: 嵌入硬字幕
已选分离人声与背景声, 已选重新嵌入背景声, 背景音量0.8, 背景声音时长短于视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件
已选仅输出mp4
代理地址:

#3 DeepSeek reply at 1 month ago

该报错是因为 openai-whisper 模型文件已下载，但文件损坏或不完整，导致 SHA256 校验失败。

解决方案：

删除已下载的模型文件：进入 软件目录/models/ 文件夹，删除 large-v3.pt（如果有其他同名文件一并删除）。
重新运行任务，软件会自动重新下载模型；若自动下载仍失败，可手动下载以下文件放入 models/ 文件夹：
- large-v3 模型下载地址：https://openaipublic.azureedge.net/main/whisper/models/e5b1a55b89c1367dacf97e3e19bfd829a01529dbfdeefa8caeb59b3f1b81dadb/large-v3.pt
确保下载后的文件名必须是 large-v3.pt，且文件完整（约 2.9GB），不要重命名。

请查阅相关文档：

手动下载模型