#6656 翻译字幕阶段出错 [Hy-MT2-1.8B(内置)] Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_textTracebac

45.207.**9 Posted at: 2 hours ago

翻译字幕阶段出错 [Hy-MT2-1.8B(内置)] Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 136, in process_task

File "videotrans\task\_stage_translate.py", line 31, in trans

File "videotrans\translator\_runner.py", line 63, in run

File "videotrans\translator\_base.py", line 68, in run

File "videotrans\translator\_base.py", line 97, in _run_text

File "videotrans\translator\_base.py", line 136, in _hymt2

File "D:\win-videotrans\_internal\transformers\__init__.py", line 786, in

sys.modules[__name__] = _LazyModule(

File "D:\win-videotrans\_internal\transformers\utils\import_utils.py", line 2009, in init

raise ValueError(

ValueError: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 批量翻译模式
原始输入文件名: D:/U2B+/XSPY Trader (Piranha Profits) - Price Action Manipulation Course/(ARCHIVED) Lesson 19 - Screening for Swing Trading Set Ups Thinkorswim Scanner.mp4,
输出结果保存到文件夹: D:/U2B+/++++/(ARCHIVED) Lesson 19 - Screening for Swing Trading Set Ups Thinkorswim Scanner-mp4,
临时文件夹: D:/win-videotrans/tmp/43212/1b4928e68c
未选 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-turbo, 发音语言: 英语, 断句方式:默认断句
翻译渠道:Hy-MT2-1.8B(内置),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, 已选 二次语音识别
音量:+0%, 语速:+0%, 未选 音频加速, 已选 视频慢速
字幕: 不嵌入字幕
代理地址:


=
system:Windows-10-10.0.26100-SP0
version:v4.08
frozen:True
language:zh
root_dir:D:/win-videotrans

1 Replies

#1 DeepSeek reply at 1 hour ago

这个问题通常是 transformers 库升级覆盖后,旧代码残留导致的 tensorflow_text 后端注册错误。

解决方案:

  1. 重新下载最新补丁包(若旧版本与当前最新版相差较大,建议下载完整包),覆盖到软件根目录 D:/win-videotrans,覆盖后重启软件再重试。
  2. 如果覆盖后仍然报错,可暂时将翻译渠道从 Hy-MT2-1.8B(内置) 切换为 DeepSeekGoogleM2M100(内置) 等渠道继续完成翻译,暂避该问题。

请查阅相关文档:

Thinking...
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.

Dondate via ko-fi.com

Related resource