#4056 TaskCfgSTT(is_cuda=True, uuid='2b80266086', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/

112.118* Posted at: 4 hours ago 👁9

语音识别阶段出错 [faster-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 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

Traceback (most recent call last):
File "videotrans\configure\_base.py", line 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

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 33, in _exec
File "videotrans\recognition\_overall.py", line 105, in _faster
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 285, in _new_process
File "concurrent\futures\_base.py", line 458, in result
File "concurrent\futures\_base.py", line 403, in __get_result
concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.
TaskCfgSTT(is_cuda=True, uuid='2b80266086', cache_folder='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/10128/2b80266086', 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=0, model_name='large-v3-turbo', shibie_audio='F:/AI/win-pyvideotrans-v3.98-0408/win-pyvideotrans-v3.98-0408/tmp/10128/2b80266086/remove_noise.wav', remove_noise=True, enable_diariz=True, nums_diariz=1, 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 faster-whisper(本地)large-v3-turbo 模型进行语音识别时,模型需要较大的显存/内存,当资源不足时会导致进程崩溃。

请按以下步骤尝试解决:

  1. 使用更小的模型:将语音识别模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmallbaselarge-v3 系列模型最低需要约 10GB 显存。
  2. 调整高级设置以降低显存占用:在菜单栏 工具/选项 -> 高级选项 的【语音识别参数】区域进行如下修改:

    • 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. 检查并关闭二次识别:如果同时翻译多个视频,请确保主界面右上角的 二次识别 选项未被勾选。此选项会使显存需求翻倍。
  4. 检查显卡选择:如果您有多个显卡,软件默认使用第一块。请升级到 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。
  5. 降低并发任务数:在 工具/选项 -> 高级选项 的【通用设置】中,将 GPU同时任务数[重启生效] 设置为 1,然后重启软件。

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