#3788 TaskCfgVTT(is_cuda=True, uuid='044d743dab', cache_folder='D:/win-pyvideotrans-v3.98-317/tmp/20444/044d743dab', target_di

221.7* Posted at: 1 hour ago 👁7

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 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\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 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
TaskCfgVTT(is_cuda=True, uuid='044d743dab', cache_folder='D:/win-pyvideotrans-v3.98-317/tmp/20444/044d743dab', target_dir='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4', source_language='英语', source_language_code='en', source_sub='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4/en.srt', source_wav='D:/win-pyvideotrans-v3.98-317/tmp/20444/044d743dab/en.wav', source_wav_output='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4/zh-cn.srt', target_wav='D:/win-pyvideotrans-v3.98-317/tmp/20444/044d743dab/target.wav', target_wav_output='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4/zh-cn.m4a', name='D:/video/Dom scalp 合集/Futex(importance)/22 Order Book Trading Terms and Lingo.mp4', noextname='22 Order Book Trading Terms and Lingo', basename='22 Order Book Trading Terms and Lingo.mp4', ext='mp4', dirname='D:/video/Dom scalp 合集/Futex(importance)', shound_del_name=None, translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='en', 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='D:/video/Dom scalp 合集/Futex(importance)/_video_out/22 Order Book Trading Terms and Lingo-mp4/22 Order Book Trading Terms and Lingo.mp4', novoice_mp4='D:/win-pyvideotrans-v3.98-317/tmp/20444/044d743dab/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:D:/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. 更换更小的模型:在语音识别渠道的下拉菜单中,将模型从 large-v3-turbo 更换为 mediumsmallbaselarge-v3 系列模型最低需要约 10GB 显存。
  2. 调整高级设置:在菜单栏 工具/选项 -> 高级选项 中进行如下修改,以降低显存占用:

    • 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。如果同时翻译多个视频,二次识别会占用额外显存。请在主界面取消勾选 二次识别 选项。
  4. 检查GPU同时任务数:在 工具/选项 -> 高级选项 -> 通用设置 中,确保 GPU同时任务数[重启生效] 设置为 1(除非单卡显存大于20G),修改后重启软件。
  5. 优化文件路径:你的视频文件路径较长且包含空格和括号(如 D:/video/Dom scalp 合集/Futex(importance)/)。建议将视频文件移动到更浅的目录(如 D:\video),并重命名为简短的英文名称(如 order_book.mp4),以避免因路径问题引发的意外错误。

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