#5854 ASR Error[faster-whisper(LocalBuilt-in)] Subprocess Error: Backend should be defined in the BACKENDS_MAPPING. Offending

2409:40e4* Posted at: 1 hour ago

ASR Error[faster-whisper(LocalBuilt-in)] Subprocess Error: 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 100, in process_task

File "videotrans\task\speech2text.py", line 97, 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=TaskCfgSTT(uuid='801eb3104c', name='G:/movies/mac checkra1n/Resources/checkra1n/The Gold Star/Loves Me, Loves Me Not 2020 English www.9kmovies.fit 720p HDRip 800MB ESubs.mkv', dirname='G:/movies/mac checkra1n/Resources/checkra1n/The Gold Star', noextname='Loves Me, Loves Me Not 2020 English www.9kmovies.fit 720p HDRip 800MB ESubs', basename='Loves Me, Loves Me Not 2020 English www.9kmovies.fit 720p HDRip 800MB ESubs.mkv', ext='mkv', target_dir='C:/Users/HP/Downloads/Compressed/win-pyvideotrans-v4.05-0711/output/recogn', cache_folder='C:/Users/HP/Downloads/Compressed/win-pyvideotrans-v4.05-0711/tmp/12872/801eb3104c', is_cuda=False, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='C:/Users/HP/Downloads/Compressed/win-pyvideotrans-v4.05-0711/output/recogn/Loves Me, Loves Me Not 2020 English www.9kmovies.fit 720p HDRip 800MB ESubs.srt', target_wav=None, target_wav_output=None, detect_language='auto', recogn_type=0, model_name='large-v3-turbo', shibie_audio='C:/Users/HP/Downloads/Compressed/win-pyvideotrans-v4.05-0711/tmp/12872/801eb3104c/Loves Me, Loves Me Not 2020 English www.9kmovies.fit 720p HDRip 800MB ESubs-1784134480.8555195.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0)


=
system:Windows-10-10.0.19045-SP0
version:v4.05
frozen:True
language:en
root_dir:C:/Users/HP/Downloads/Compressed/win-pyvideotrans-v4.05-0711

1 Replies

The error Backend should be defined in the BACKENDS_MAPPING. Offending backend: tensorflow_text indicates that the tensorflow_text library—a dependency required by the faster‑whisper backend—is missing or not properly registered in your environment.

Root Cause
The packaged sp.exe expects tensorflow_text to be present. If you're using the full green package (2.6GB+), this component is included; if you accidentally downloaded only the patch package (~260MB), the required dependencies are incomplete.

Solution

  1. Ensure you have the full package – Download the complete 2.6GB win-pyvideotrans-v4.05-0711.7z from the official site, extract it fully, and then do not overwrite with the patch unless you already have the full base.
  2. Re‑extract to a simple, short path – Move the extracted folder to a location with only English letters, digits, and underscores (e.g., D:\pyVideoTrans). Avoid long file names, spaces, and special characters — your current video path contains many dots, spaces, and a long name, which can also trigger ffmpeg/whisper issues.
  3. Run as administrator once – Right‑click sp.exe → "Run as administrator" to ensure all dependencies load correctly.
  4. Verify CUDA/GPU is NOT required – The error occurs even without CUDA, but if you have an NVIDIA GPU, make sure CUDA 12.8+ and cuDNN 9.11+ are installed. The log shows is_cuda=False, so CUDA is not the cause here.

If the problem persists after following the steps above, please provide the contents of the latest log file from logs/ (the file ending with .log for today’s date) so we can investigate further.

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