#3739 TaskCfgVTT(is_cuda=True, uuid='87fb8f3144', cache_folder='E:/APP/win-pyvideotrans-v3.98-317/tmp/16240/87fb8f3144', targe

2408:8262* Posted at: 4 hours ago 👁12

语音识别阶段出错 [faster-whisper(本地)] 出错了,可能内存或显存不足 [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\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 33, in _exec
File "videotrans\recognition\_overall.py", line 105, in _faster
File "videotrans\configure\_base.py", line 299, in _new_process
RuntimeError: 出错了,可能内存或显存不足 [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.
TaskCfgVTT(is_cuda=True, uuid='87fb8f3144', cache_folder='E:/APP/win-pyvideotrans-v3.98-317/tmp/16240/87fb8f3144', target_dir='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4', source_language='日语', source_language_code='ja', source_sub='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4/ja.srt', source_wav='E:/APP/win-pyvideotrans-v3.98-317/tmp/16240/87fb8f3144/ja.wav', source_wav_output='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4/ja.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4/zh-cn.srt', target_wav='E:/APP/win-pyvideotrans-v3.98-317/tmp/16240/87fb8f3144/target.wav', target_wav_output='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4/zh-cn.m4a', name='F:/影音/4 Temp/新建文件夹/av/[email protected]4', noextname='489155.com@NHDTC-155', basename='[email protected]4', ext='mp4', dirname='F:/影音/4 Temp/新建文件夹/av', 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=False, remove_silent_mid=False, align_sub_audio=True, detect_language='ja', recogn_type=0, 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='tiqu', subtitles='', targetdir_mp4='F:/影音/4 Temp/新建文件夹/av/_video_out/489155.com@NHDTC-155-mp4/[email protected]4', novoice_mp4='E:/APP/win-pyvideotrans-v3.98-317/tmp/16240/87fb8f3144/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=True, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=True)


=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:zh
root_dir:E:/APP/win-pyvideotrans-v3.98-317

1 Replies

这是由于显存或内存不足导致的。错误信息明确指出“可能内存或显存不足 [GPU0]”,并且使用了 large-v3-turbo 模型,该模型对显存要求较高。

解决方案:

  1. 更换更小的语音识别模型: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 mediumsmallbaselarge-v3 系列模型最低需要 8GB 显存,但实际运行时,其他程序也会占用显存。
  2. 调整高级设置以降低显存占用:在顶部菜单栏 工具/选项 -> 高级选项 中进行如下修改:

    • 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. 检查并优化系统资源:关闭其他占用大量显存或内存的程序(如游戏、大型设计软件),确保有足够的可用资源供软件使用。
  4. 考虑使用在线语音识别渠道:如果本地硬件资源确实有限,可以尝试使用在线语音识别渠道(如 OpenAI API、阿里百炼 Qwen3-ASR),这些服务不依赖本地显存。

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