#4769 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 GPU0Traceback (most recent call last): File "D:\GitClo

72.56* Posted at: 4 hours ago

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 "D:\GitClone\pyvideotrans\videotrans\configure\_base.py", line 285, in _new_process

_rs = future.result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 458, in result

return self.__get_result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 403, in __get_result

raise self._exception

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 "D:\GitClone\pyvideotrans\videotrans\configure\_base.py", line 285, in _new_process

_rs = future.result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 458, in result

return self.__get_result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 403, in __get_result

raise self._exception

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 "D:\GitClone\pyvideotrans\videotrans\task\job.py", line 105, in run

trk.recogn()

File "D:\GitClone\pyvideotrans\videotrans\task\_speech2text.py", line 159, in recogn

raw_subtitles = run(

File "D:\GitClone\pyvideotrans\videotrans\recognition\__init__.py", line 293, in run

return FasterAll(**kwargs).run()

File "D:\GitClone\pyvideotrans\videotrans\recognition\_base.py", line 143, in run

res = self._exec()

File "D:\GitClone\pyvideotrans\videotrans\recognition\_overall.py", line 33, in _exec

raws = self._faster()

File "D:\GitClone\pyvideotrans\videotrans\recognition\_overall.py", line 105, in _faster

raws=self._new_process(callback=faster_whisper,title=title,is_cuda=self.is_cuda,kwargs=kwargs)

File "D:\GitClone\pyvideotrans\videotrans\configure\_base.py", line 303, in _new_process

raise RuntimeError(f'{tr("may be insufficient memory")}{_model}{_cuda} {err}')

RuntimeError: 出错了,可能内存或显存不足 Model:large-v3-turbo GPU0
Traceback (most recent call last):
File "D:\GitClone\pyvideotrans\videotrans\configure\_base.py", line 285, in _new_process

_rs = future.result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 458, in result

return self.__get_result()

File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.19-windows-x86_64-none\lib\concurrent\futures\_base.py", line 403, in __get_result

raise self._exception

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='e39922d3fc', cache_folder='D:/GitClone/pyvideotrans/tmp/16632/e39922d3fc', target_dir='d:/gitclone/pyvideotrans/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="d:/gitclone/pyvideotrans/output/recogn/21 - Euler's Method (Numerical Solutions for Differential Equations).srt", target_wav=None, target_wav_output=None, name="D:/YoutubeDownloads/Houston Math Prep/Differential Equations/21 - Euler's Method (Numerical Solutions for Differential Equations).mkv", noextname="21 - Euler's Method (Numerical Solutions for Differential Equations)", basename="21 - Euler's Method (Numerical Solutions for Differential Equations).mkv", ext='mkv', dirname='D:/YoutubeDownloads/Houston Math Prep/Differential Equations', shound_del_name=None, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio="D:/GitClone/pyvideotrans/tmp/16632/e39922d3fc/21 - Euler's Method (Numerical Solutions for Differential Equations)-1779974010.2276707.wav", remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.99
frozen:False
language:zh
root_dir:D:/GitClone/pyvideotrans
Python: 3.10.19 (main, Feb 12 2026, 00:37:08) [MSC v.1944 64 bit (AMD64)]

1 Replies

这是由于显存不足导致 Faster-Whisper 子进程被系统强制终止。large-v3-turbo 模型通常需要 6-8GB 以上显存,当前显卡(GPU0)可能无法满足。

请按以下顺序尝试解决:

  1. 更换更小的模型:在语音识别渠道中将模型改为 mediumsmallbase,降低显存需求。
  2. 调整高级设置降低显存占用:菜单 → 工具/选项 → 高级选项 → 语音识别参数,将:

    • CUDA数据类型 改为 float16int8
    • beam_size 改为 1
    • best_of 改为 1
    • 启用上下文感知 改为 false
  3. 检查是否有其他程序占用显存:关闭浏览器、其他 AI 工具等,释放显存。
  4. 若有多张显卡:软件默认使用第一块显卡。可在高级选项中启用 多显卡模式,或确保当前 GPU 显存充足。

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