#4065 TaskCfgVTT(is_cuda=True, uuid='3d958ad971', cache_folder='D:/pyvideotrans/tmp/6324/3d958ad971', target_dir='C:/Users/Adm

206.237* Posted at: 3 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='3d958ad971', cache_folder='D:/pyvideotrans/tmp/6324/3d958ad971', target_dir='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4', source_language='英语', source_language_code='en', source_sub='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4/en.srt', source_wav='D:/pyvideotrans/tmp/6324/3d958ad971/en.wav', source_wav_output='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4/zh-cn.srt', target_wav='D:/pyvideotrans/tmp/6324/3d958ad971/target.wav', target_wav_output='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4/zh-cn.m4a', name='C:/Users/Administrator/Downloads/Kids Realise They Accidentally Killed Their Best Friend.mp4', noextname='Kids Realise They Accidentally Killed Their Best Friend', basename='Kids Realise They Accidentally Killed Their Best Friend.mp4', ext='mp4', dirname='C:/Users/Administrator/Downloads', shound_del_name=None, translate_type=0, tts_type=10, 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='C:/Users/Administrator/Downloads/_video_out/Kids Realise They Accidentally Killed Their Best Friend-mp4/Kids Realise They Accidentally Killed Their Best Friend.mp4', novoice_mp4='D:/pyvideotrans/tmp/6324/3d958ad971/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=0, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.26100-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/pyvideotrans

1 Replies

这是由于显存或内存不足导致语音识别进程崩溃。从日志可见,你使用了 faster-whisper(本地)large-v3-turbo 模型,并启用了 CUDA 加速 (is_cuda=True),但进程池被意外终止,提示可能内存或显存不足。

解决方案:

  1. 降低模型大小:在语音识别下拉菜单中,将模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmalllarge-v3 系列模型对显存要求较高(通常需要 10GB 以上)。
  2. 调整高级设置:进入 菜单 -> 工具/选项 -> 高级选项,在 【语音识别参数】 区域进行以下调整,以降低显存/内存占用:

    • CUDA数据类型:从 float32 改为 float16int8
    • 识别准确度beam_size:从 5 改为 1
    • 识别准确度best_of:从 5 改为 1
    • 启用上下文感知:确保此项为 false(不勾选)。
  3. 检查并限制并发任务:在 【通用设置】 区域,确保 GPU同时任务数[重启生效] 设置为 1(除非你的单张显卡显存大于20GB)。修改后需要重启软件生效。
  4. 关闭二次识别:从日志 recogn2pass=True 可见你开启了“二次识别”。在处理多个视频时,二次识别可能与首次识别同时运行,导致显存需求翻倍。在主界面右上角取消勾选“二次识别”,可以显著降低显存压力。
  5. 检查可用显存:使用 nvidia-smi 命令查看你的显卡可用显存。如果显存小于 8GB,使用 large-v3-turbo 模型风险很高,强烈建议执行第1步。
  6. 使用 CPU 模式:如果显卡显存确实太小,可以尝试取消勾选主界面右上角的“CUDA加速”,让模型在 CPU 上运行(速度会慢很多,但能避免显存不足)。

执行顺序建议:首先执行第4步(关闭二次识别)并重试。如果问题依旧,依次尝试第1步、第2步和第3步。

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