#2931 TaskCfg(cache_folder='C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95/tmp/19436/2b44cc8eab', target_dir='C:/User

152.237* Posted at: 2 hours ago 👁4

ASR Error [faster-whisper (Local)] An error has occurred. There may be insufficient memory or video memory. Please try changing the faster-whisper batch size to 1 in the advanced options.
A child process terminated abruptly, the process pool is not usable anymore
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 268, in _new_process
File "videotrans\process\signelobj.py", line 79, in submit_task_gpu
File "concurrent\futures\process.py", line 689, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\task\job.py", line 106, in run
File "videotrans\task\trans_create.py", line 358, in recogn
File "videotrans\recognition\__init__.py", line 276, in run
File "videotrans\recognition\_base.py", line 140, in run
File "videotrans\recognition\_overall.py", line 63, in _exec
File "videotrans\recognition\_overall.py", line 142, in _faster
File "videotrans\configure\_base.py", line 282, in _new_process
RuntimeError: An error has occurred. There may be insufficient memory or video memory. Please try changing the faster-whisper batch size to 1 in the advanced options.
A child process terminated abruptly, the process pool is not usable anymore
TaskCfg(cache_folder='C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95/tmp/19436/2b44cc8eab', target_dir='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4', remove_noise=False, is_separate=False, detect_language='en', subtitle_language=None, source_language='English', target_language='Portuguese', source_language_code='en', target_language_code='pt', source_sub='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4/en.srt', target_sub='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4/pt.srt', source_wav='C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95/tmp/19436/2b44cc8eab/en.wav', source_wav_output='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4/en.m4a', target_wav='C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95/tmp/19436/2b44cc8eab/target.wav', target_wav_output='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4/pt.m4a', subtitles='', novoice_mp4='C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95/tmp/19436/2b44cc8eab/novoice.mp4', noextname='11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)', shibie_audio=None, targetdir_mp4='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/_video_out/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module)-mp4/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module).mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='biaozhun', subtitle_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=0, model_name='large-v3-turbo', voice_autorate=False, video_autorate=False, cuda=True, name='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL/11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module).mp4', basename='11. Create Blood Bank Management System in C# (Creating Business Logic Layer for Donor Module).mp4', ext='mp4', dirname='C:/Users/JOHN/Documents/Curso_C#/BANCO DE SANGUE/ORIGINAL', shound_del_name=None, uuid='2b44cc8eab', remove_silent_mid=False, align_sub_audio=False, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False, fix_punc=False, recogn2pass=False)

=
system:Windows-10-10.0.19045-SP0
version:v3.95
frozen:True
language:en
root_dir:C:/Users/JOHN/Documents/DUBLADOR/win-pyvideotrans-v3.95

1 Replies

Floor #1 DeepSeek Posted at 2 hours ago

This error is caused by insufficient GPU memory (VRAM) when running the faster-whisper model.

The error message explicitly states: "There may be insufficient memory or video memory." The BrokenProcessPool indicates a sub-process crashed, typically due to the GPU running out of memory while loading or processing the large-v3-turbo model.

Solution Steps:

  1. Reduce GPU Memory Usage (Immediate Fix):

    • Go to the software's menu: Tools -> Advanced Options.
    • In the Speech Recognition Parameters section, find the setting for faster-whisper batch size.
    • Change this value to 1 (as suggested by the error message) and save the settings.
    • Restart the software and try the task again.

  2. Use a Smaller Model (If Step 1 Fails):

    • In the main interface, under Speech Recognition Channel, select faster-whisper (Local).
    • Click the Settings button next to it.
    • Change the Model from large-v3-turbo to a smaller one like large-v2, medium, or small. Smaller models require significantly less VRAM.

  3. Enable Model Quantization (Advanced):

    • In the same faster-whisper Settings window, look for the Compute Type option.
    • Try changing it to int8. This reduces the model's precision and memory footprint, often allowing larger models to run on limited VRAM, though it may slightly reduce accuracy.

  4. General Memory Management:

    • Close any other applications that might be using your GPU (e.g., other AI tools, games, browsers).
    • Ensure you have the latest NVIDIA drivers installed.
    • Verify that CUDA is correctly installed and configured for GPU acceleration (Knowledge Base Section 2.3).

If the problem persists after trying the above steps, your GPU's VRAM may be insufficient for the selected model. Consider using an online speech recognition API (like OpenAI Whisper API) or processing shorter video segments.

Please refer to the relevant documentation:

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.

Related resource

Similar issues already exist