#5785 Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tfTraceback (most recent call la

91.38* Posted at: 2 days ago

Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tf
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 46, in run
File "videotrans\task\_stage_recogn.py", line 62, in recogn
File "videotrans\recognition\__init__.py", line 205, in run
File "videotrans\recognition\_base.py", line 91, in run
File "videotrans\recognition\_whisper.py", line 38, in _exec
File "videotrans\recognition\_whisper.py", line 124, in _faster
File "videotrans\configure\base.py", line 272, in _new_process
videotrans.configure.excepts.VideoTransError: Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tf

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: C:/Users/BK/Videos/Ernst Veter Course RU/Ernst Veter 1.mp4,
输出结果保存到文件夹: C:/Users/BK/Videos/Ernst Veter Course RU/_video_out/Ernst Veter 1-mp4,
临时文件夹: C:/Users/BK/Downloads/win-pyvideotrans-v4.05-0711/tmp/8644/72a159bff0
已选清理已存在
已选启用CUDA加速
未选降噪
ASR Channel:faster-whisper(LocalBuilt-in), model_name: large-v3-turbo, 发音语言: Russian, 断句方式:默认断句
Trans Channel:Google (Free),原始语言:Russian,目标语言:English, 已选 Send SRT
Dubb Channel:Edge-TTS(Free), 角色:Steffan(Male/US), 配音语言:English, 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: Embed Hard Subs
代理地址:

=
system:Windows-10-10.0.26200-SP0
version:v4.05
frozen:True
language:en
root_dir:C:/Users/BK/Downloads/win-pyvideotrans-v4.05-0711

Floor #1 DeepSeek reply at 2 days ago

Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tf indicates a conflict in CTranslate2’s internal TensorFlow backend, likely triggered by an incompatible ctranslate2 version or a corrupted environment. This usually occurs when using faster-whisper with CUDA on Windows.

Solution:

Switch to openai-whisper (local built-in) as a workaround – it does not depend on ctranslate2:
- In the main interface, change ASR Channel from faster-whisper to openai-whisper and select model large-v3.
If you must use faster-whisper, try these fixes:
- Clear the model cache: delete the folder models/models--Systran--faster-whisper-large-v3-turbo and let the software re-download it.
- In Advanced Options → Speech Recognition Parameters, set Compute Type to int8 (avoids TensorFlow path issues).
- Disable CUDA temporarily (uncheck "Enable CUDA") – if the error disappears, the GPU driver or cudnn/cublas integration may be mismatched. Reinstall the correct CUDA 12.8 + cuDNN 9.11.
Update to the latest version – the bug might be fixed in a newer release. Download the latest full package from official releases.

If the problem persists, please provide the full log file from logs/ folder for further analysis.

#5785 Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tfTraceback (most recent call la

1 Replies

Post Your Reply

Related resource