#3710 TaskCfgVTT(is_cuda=True, uuid='1959489614', cache_folder='C:/Users/joby8/Downloads/pyvideotrans/tmp/25688/1959489614', t

116.68* Posted at: 1 hour ago 👁9

ASR Error [openai-whisper (Local)] An error has occurred. There may be insufficient memory or video memory. [GPU0]
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore

Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, 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 105, in run
File "videotrans\task\trans_create.py", line 360, in recogn
File "videotrans\recognition\__init__.py", line 272, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_overall.py", line 31, in _exec
File "videotrans\recognition\_overall.py", line 73, in _openai
File "videotrans\configure\_base.py", line 299, in _new_process
RuntimeError: An error has occurred. There may be insufficient memory or video memory. [GPU0]
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 281, in _new_process
File "videotrans\process\signelobj.py", line 80, in submit_task_gpu
File "concurrent\futures\process.py", line 720, in submit
concurrent.futures.process.BrokenProcessPool: A child process terminated abruptly, the process pool is not usable anymore
TaskCfgVTT(is_cuda=True, uuid='1959489614', cache_folder='C:/Users/joby8/Downloads/pyvideotrans/tmp/25688/1959489614', target_dir='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4', source_language='German', source_language_code='de', source_sub='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4/de.srt', source_wav='C:/Users/joby8/Downloads/pyvideotrans/tmp/25688/1959489614/de.wav', source_wav_output='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4/de.m4a', target_language='English', target_language_code='en', target_sub='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4/en.srt', target_wav='C:/Users/joby8/Downloads/pyvideotrans/tmp/25688/1959489614/target.wav', target_wav_output='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4/en.m4a', name='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/4 Apple Style - Widget Animations.mp4', noextname='4 Apple Style - Widget Animations', basename='4 Apple Style - Widget Animations.mp4', ext='mp4', dirname='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100', shound_del_name=None, translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Ryan(Male/GB)', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='de', recogn_type=1, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/Courses/Shortcut/AfterEffects Advanced/Breakdown Tutorials – From 0 to 100/_video_out/4 Apple Style - Widget Animations-mp4/4 Apple Style - Widget Animations.mp4', novoice_mp4='C:/Users/joby8/Downloads/pyvideotrans/tmp/25688/1959489614/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:en
root_dir:C:/Users/joby8/Downloads/pyvideotrans

3 Replies

Floor #1 DeepSeek AI reply at 1 hour ago

This error is caused by insufficient GPU memory (VRAM) when using the openai-whisper (local) model with CUDA acceleration.

To resolve this, follow these steps:

  1. Switch to a smaller ASR model: In the main interface, change the speech recognition model from large-v3-turbo to a smaller one like medium, small, or base. The large-v3-turbo model requires significant VRAM.

  2. Adjust advanced settings to reduce VRAM usage: Go to Menu -> Tools/Options -> Advanced Options. In the "Speech Recognition Parameters" section, make the following adjustments:

    • Set CUDA Data Type to float16 or int8 (instead of float32).
    • Set beam_size to 1.
    • Set best_of to 1.
    • Set Enable Context Awareness to false.
  3. Ensure only one GPU task is running: In the same "Advanced Options" menu, under "General Settings", verify that GPU Concurrent Task Count [Restart Required] is set to 1. This is the default and safest setting unless you have a GPU with more than 20GB of VRAM.
  4. Check for multiple GPUs: If you have more than one NVIDIA GPU, the software might be attempting to use the one with less available VRAM by default. Ensure the primary GPU has sufficient free memory. Version v3.98-317 and later will automatically select the GPU with the largest available VRAM.

If the issue persists after trying the above, your video might be too long for your available VRAM. You can also try using the faster-whisper (local) model with a smaller size, as it is generally more memory-efficient.

Please refer to the relevant documentation:

Floor #2 116.68* reply at 1 hour ago

thanks,. changed from large to medium. works.

Floor #3 DeepSeek AI reply at 1 hour ago

Good. Switching to a smaller model (medium) is the standard solution for insufficient GPU memory (VRAM) errors. If you need to process longer videos or want to try improving accuracy within your hardware limits, you can further adjust the advanced settings mentioned previously.

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