#3960 TaskCfgVTT(is_cuda=True, uuid='49eb0faa0d', cache_folder='G:/VideoTrans/tmp/2536/49eb0faa0d', target_dir='D:/Bl tuatriol

119.123* Posted at: 4 hours ago 👁8

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\trans_create.py", line 360, 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.
TaskCfgVTT(is_cuda=True, uuid='49eb0faa0d', cache_folder='G:/VideoTrans/tmp/2536/49eb0faa0d', target_dir='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4', source_language='英语', source_language_code='en', source_sub='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4/en.srt', source_wav='G:/VideoTrans/tmp/2536/49eb0faa0d/en.wav', source_wav_output='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4/zh-cn.srt', target_wav='G:/VideoTrans/tmp/2536/49eb0faa0d/target.wav', target_wav_output='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4/zh-cn.m4a', name='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/71. 04_01 Walk Cycles Animation.mp4', noextname='71. 04_01 Walk Cycles Animation', basename='71. 04_01 Walk Cycles Animation.mp4', ext='mp4', dirname='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation', shound_del_name=None, translate_type=0, tts_type=11, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='001.wav', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=True, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/04/71. 04_01 Walk Cycles Animation-mp4/71. 04_01 Walk Cycles Animation.mp4', novoice_mp4='G:/VideoTrans/tmp/2536/49eb0faa0d/novoice.mp4', is_separate=True, embed_bgm=True, instrument='G:/VideoTrans/tmp/2536/49eb0faa0d/instrument.wav', vocal='G:/VideoTrans/tmp/2536/49eb0faa0d/vocal.wav', back_audio='', clear_cache=False, background_music=None, subtitle_type=1, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:G:/VideoTrans

1 Replies

这是由于显存或内存不足导致的。错误信息明确指出在使用 faster-whisper(本地)large-v3-turbo 模型时,GPU0 的显存或系统内存不足,导致进程池崩溃。

解决方案:

  1. 降低模型大小:将语音识别模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmallbaselarge-v3-turbo 模型对显存要求较高。
  2. 调整高级设置:在菜单栏 工具/选项 -> 高级选项 中,进入“语音识别参数”区域,进行如下修改以降低资源占用:

    • 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:从日志中看到 recogn2pass=True,即开启了二次识别。这会额外消耗显存。请在主界面右上角取消勾选 二次识别 选项,尤其是在批量处理时。
  4. 确保单任务运行:在 工具/选项 -> 高级选项 的“通用设置”中,确认 GPU同时任务数[重启生效] 设置为 1(除非你的单卡显存大于20GB),并重启软件。
  5. 优化文件路径:你的原始视频文件路径 D:/Bl tuatriol/A Z Guide/4 - Chapter 4 Advanced Animation/71. 04_01 Walk Cycles Animation.mp4 较长且包含空格。建议将视频文件复制到更浅的目录(如 D:/videos),并重命名为一个简短的英文名称(如 walk_cycle.mp4),以避免潜在的路径处理问题。

如果以上步骤仍无法解决,请尝试:

  • 如果电脑有多个显卡,且第一块显卡(GPU0)显存较小,可以尝试升级到 v3.98-317 或更高版本,该版本会默认使用可用显存最大的显卡。
  • 如果完全没有 NVIDIA 显卡或未正确配置 CUDA,请取消勾选主界面的 CUDA加速 选项,但这会使处理速度大幅下降。

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