#4057 TaskCfgSTT(is_cuda=True, uuid='d60f6dd9b6', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/

149.88* Posted at: 3 hours ago 👁9

语音识别阶段出错 [openai-whisper(本地)] 出错了,可能内存或显存不足 Model:large-v3-turbo 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\_speech2text.py", line 159, in recogn
File "videotrans\recognition\__init__.py", line 292, 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 303, in _new_process
RuntimeError: 出错了,可能内存或显存不足 Model:large-v3-turbo 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
TaskCfgSTT(is_cuda=True, uuid='d60f6dd9b6', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/27268/d60f6dd9b6', target_dir='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/output/recogn', 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='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/output/recogn/Elitepainc_Myra.srt', target_wav=None, target_wav_output=None, name='G:/IntelMSI/4雜/Elitepainc_Myra.mp4', noextname='Elitepainc_Myra', basename='Elitepainc_Myra.mp4', ext='mp4', dirname='G:/IntelMSI/4雜', shound_del_name=None, detect_language='fr', recogn_type=1, model_name='large-v3-turbo', shibie_audio='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/27268/d60f6dd9b6/remove_noise.wav', remove_noise=True, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408

1 Replies

这是由于显存或内存不足导致的。在使用 openai-whisper(本地)large-v3-turbo 模型进行语音识别时,该模型对显存/内存需求较高,导致子进程崩溃。

解决方案:

  1. 使用更小的模型:在主界面的语音识别渠道下拉菜单中,将模型从 large-v3-turbo 更换为 mediumsmallbase
  2. 调整高级设置以降低资源占用:进入 菜单 -> 工具/选项 -> 高级选项,在“语音识别参数”区域进行以下调整:

    • CUDA数据类型:将 float32 改为 float16int8
    • 识别准确度beam_size:将 5 改为 1
    • 识别准确度best_of:将 5 改为 1
    • 启用上下文感知:将 true 改为 false
  3. 检查二次识别:如果你在翻译视频时勾选了“二次识别”,请先取消勾选。因为二次识别会再次运行语音识别模型,可能占用双倍显存。
  4. 检查多显卡配置:如果你有多个显卡,且第一个显卡的可用显存较小,软件可能默认使用了它。可以尝试升级到 v3.98-317 或更高版本,该版本会自动选择可用显存最大的显卡。或者,在“高级选项”中,将 GPU同时任务数 设为 1,并禁用 多显卡模式
  5. 关闭其他占用显存的程序:确保没有其他大型软件(如游戏、3D建模软件)同时运行。

请查阅相关文档:

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