#5752 Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_textTraceback (most r

150.107* Posted at: 4 days ago

Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text
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: 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: C:/Users/MSI/Downloads/best_accounting_software_for_freelancers.mp3,
输出结果保存到文件夹: C:/Users/MSI/Downloads/_video_out/best_accounting_software_for_freelancers-mp3,
临时文件夹: D:/PyVideoTrans/tmp/23980/5c560957c2
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: English, 断句方式:默认断句
Trans Channel:Microsoft (Free),原始语言:English,目标语言:Spanish, 已选 Send SRT
Dubb Channel:Qwen3-TTS(LocalBuilt-in), 角色:clone, 配音语言:Spanish, 未选二次语音识别
音量:+0%, 语速:+0%, 未选音频加速, 未选视频慢速
未选移除字幕间空隙, 已选强制对齐字幕和声音
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:D:/PyVideoTrans

Floor #1 DeepSeek reply at 4 days ago

This error is caused by a missing or incompatible TensorFlow-related backend (tensorflow_text) within the faster-whisper subprocess. This is not a typical faster-whisper error but likely stems from a corrupted dependency or cached runtime environment in your Windows pre-packaged version.

Steps to Resolve:

Restart the software completely – Sometimes a stale subprocess is the culprit.
Clear all temporary files – Go to D:/PyVideoTrans/tmp/ and delete the entire contents. Also manually delete the cache folder for the specific task (5c560957c2 if it exists).
Re-download the latest full release – Ensure you have the correct complete package (not just a patch). The full package is ~2.6GB. The error may come from a corrupt update.
Verify your CUDA and cuDNN installation – Open a command prompt and run nvcc -V. If the version is not 12.8+, reinstall CUDA toolkit 12.8 and cuDNN 9.11. A misconfigured CUDA environment can cause unpredictable TensorFlow subprocess crashes.
Disable GPU acceleration temporarily – Uncheck "CUDA Acceleration" and try again. If the error disappears, the issue is GPU-related.
Re-download the large-v3-turbo model – Manually delete the model folder models/models--mobiuslabsgmbh--faster-whisper-large-v3-turbo and let the software download it fresh.

If the error persists, please share the log file from D:/PyVideoTrans/logs/ (the newest .log file) with the last 30 lines of error output. Also confirm your software version is exactly v4.05 (visible in the top-left corner of the GUI).

#5752 Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_textTraceback (most r

1 Replies

Steps to Resolve:

Post Your Reply

Related resource