#3886 TaskCfgVTT(is_cuda=True, uuid='e6d4edf30a', cache_folder='E:/3.98/tmp/7468/e6d4edf30a', target_dir='E:/BaiduNetdiskDownl

2405:4802* Posted at: 1 day ago 👁28

ASR Error [Qwen-ASR(Local)] An error has occurred. There may be insufficient memory or video memory.
A child process terminated abruptly, the process pool is not usable anymore
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 280, in _new_process
File "videotrans\process\signelobj.py", line 81, 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 353, in recogn
File "videotrans\recognition\__init__.py", line 239, in run
File "videotrans\recognition\_base.py", line 143, in run
File "videotrans\recognition\_qwenasrlocal.py", line 48, in _exec
File "videotrans\configure\_base.py", line 294, in _new_process
RuntimeError: An error has occurred. There may be insufficient memory or video memory.
A child process terminated abruptly, the process pool is not usable anymore
TaskCfgVTT(is_cuda=True, uuid='e6d4edf30a', cache_folder='E:/3.98/tmp/7468/e6d4edf30a', target_dir='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4', source_language='Simplified Chinese', source_language_code='zh-cn', source_sub='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4/zh-cn.srt', source_wav='E:/3.98/tmp/7468/e6d4edf30a/zh-cn.wav', source_wav_output='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4/zh-cn.m4a', target_language='-', target_language_code=None, target_sub='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4/None.srt', target_wav='E:/3.98/tmp/7468/e6d4edf30a/target.wav', target_wav_output='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4/None.m4a', name='E:/BaiduNetdiskDownload/krenz构成第14期/250423构成14期-入学典礼.mp4', noextname='250423构成14期-入学典礼', basename='250423构成14期-入学典礼.mp4', ext='mp4', dirname='E:/BaiduNetdiskDownload/krenz构成第14期', shound_del_name=None, translate_type=8, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', recogn_type=2, model_name='1.7B', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='tiqu', subtitles='', targetdir_mp4='E:/BaiduNetdiskDownload/krenz构成第14期/_video_out/250423构成14期-入学典礼-mp4/250423构成14期-入学典礼.mp4', novoice_mp4='E:/3.98/tmp/7468/e6d4edf30a/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=False, output_srt=0, copysrt_rawvideo=False)

=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:en
root_dir:E:/3.98

1 Replies

Floor #1 DeepSeek AI reply at 1 day ago

This error is caused by insufficient memory or video memory (VRAM) when using the Qwen-ASR (Local) model for speech recognition.

The error message A child process terminated abruptly, the process pool is not usable anymore and RuntimeError: An error has occurred. There may be insufficient memory or video memory. indicate that the process handling the ASR task crashed, likely due to the system running out of available RAM or the GPU running out of VRAM.

Solution Steps:

  1. Use a smaller ASR model: The log shows you are using the Qwen-ASR model with model_name='1.7B'. This model is relatively large. Switch to a smaller, faster model.

    • In the main interface, under "Speech Recognition," change the channel from Qwen-ASR(Local) to faster-whisper(local).
    • For the model, select medium or small instead of large-v3. This significantly reduces memory/VRAM requirements while maintaining decent accuracy for Chinese.

  2. Adjust Advanced Settings to reduce resource usage: Go to Menu -> Tools/Options -> Advanced Options.

    • In the "Speech Recognition Parameters" section:

      • Set CUDA Data Type to float16 or int8 (consumes less VRAM, slightly lower precision).
      • Set Recognition Accuracy beam_size to 1.
      • Set Recognition Accuracy best_of to 1.
      • Set Enable Context Awareness to false.

    • In the "General Settings" section:

      • Ensure GPU Simultaneous Tasks [Restart Effective] is set to 1 (default). Do not increase this unless you have a GPU with more than 20GB VRAM.
  3. Check for concurrent tasks: If you are processing multiple videos simultaneously or have "Secondary Recognition" enabled, it can double the VRAM usage. Try processing one video at a time and disable "Secondary Recognition" in the main interface.
  4. Verify CUDA installation (if using GPU): The log shows is_cuda=True. Ensure you have CUDA 12.8 and a compatible cuDNN version installed correctly. Run nvcc -V in Command Prompt to check. An outdated or incorrect CUDA version can cause instability.
  5. Free up system memory: Close other memory-intensive applications (browsers, games, other AI software) before running pyVideoTrans.

If the issue persists after trying the above steps, the video file might be too long for your system's available memory. You can try splitting the video into shorter segments before processing.

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