#6441 Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_textTraceback (most recent call last):

112.224.**0 Posted at: 1 hour ago

Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 83, in run
File "videotrans\task\_stage_translate.py", line 31, in trans
File "videotrans\translator\_runner.py", line 59, in run
File "videotrans\__init__.py", line 28, in get_class
File "importlib\__init__.py", line 126, in import_module
File "", line 1050, in _gcd_import
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "pyimod02_importers.py", line 457, in exec_module
File "videotrans\translator\_m2m100.py", line 3, in
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "pyimod02_importers.py", line 457, in exec_module
File "ctranslate2\__init__.py", line 58, in
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "pyimod02_importers.py", line 457, in exec_module
File "ctranslate2\converters\__init__.py", line 8, in
File "", line 1027, in _find_and_load
File "", line 1006, in _find_and_load_unlocked
File "", line 688, in _load_unlocked
File "pyimod02_importers.py", line 457, in exec_module
File "ctranslate2\converters\transformers.py", line 14, in
File "D:\videotrans\pyvideotrans40602\_internal\transformers\__init__.py", line 786, in

sys.modules[__name__] = _LazyModule(

File "D:\videotrans\pyvideotrans40602\_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 单视频模式
原始输入文件名: D:/迅雷下载/筛选区/突发:朝鲜再射短程弹道导弹,半岛紧张升级.mp4,
输出结果保存到文件夹: 突发:朝鲜再射短程弹道导弹,半岛紧张升级-mp4,
临时文件夹: D:/videotrans/pyvideotrans40602/tmp/7632/db890f1b21
未选 清理已存在
未启用CUDA加速
未选 降噪
语音识别:openai-whisper(内置), model_name: large-v3-turbo, 发音语言: 韩语, 断句方式:默认断句
翻译渠道:M2M100(内置),原始语言:韩语,目标语言:简体中文, 已选 发送完整字幕
未选 配音角色,不进行配音
字幕: 嵌入硬字幕
代理地址:


=
system:Windows-10-10.0.19045-SP0
version:v4.08
frozen:True
language:zh
root_dir:D:/videotrans/pyvideotrans40602

1 Replies

这是升级时 transformers 库混入旧文件导致的已知兼容性问题,错误发生在 ctranslate2 加载 transformers 模块时,通常在使用 M2M100 内置翻译渠道时触发。

解决方法(按顺序尝试):

  1. 下载最新补丁包覆盖:当前 v4.08 已发布 v4.08-0802 修复版,前往官网 https://pyvideotrans.com/downpackage 下载最新补丁包,解压后覆盖到软件根目录(覆盖前建议先备份 videotrans/params.jsonvideotrans/cfg.json)。
  2. 若补丁包覆盖后仍报错,说明本地依赖残留较多,建议直接下载 2.7GB 完整包重新解压,再放入你的配置文件。
  3. 临时方案:在「翻译渠道」中暂时改用其他翻译渠道,例如 DeepSeek(需在菜单-翻译设置中填写密钥)或 Google 翻译 / 微软翻译,避开 M2M100 的 ctranslate2 依赖路径。

另外提示:当前输入视频路径和文件名包含中文及特殊符号(如冒号、逗号),建议后续将视频移动/重命名为纯英文路径(如 D:/videos/test.mp4),否则后续 FFmpeg 合成阶段也容易出现解析异常。

请查阅相关文档:

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

Dondate via PayPal

Related resource