#3715 TaskCfgVTT(is_cuda=True, uuid='a7a3cfacc9', cache_folder='E:/win-pyvideotrans-v3.98-317/tmp/15420/a7a3cfacc9', target_di

198.98* Posted at: 2 hours ago 👁9

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='a7a3cfacc9', cache_folder='E:/win-pyvideotrans-v3.98-317/tmp/15420/a7a3cfacc9', target_dir='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4', source_language='英语', source_language_code='en', source_sub='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4/en.srt', source_wav='E:/win-pyvideotrans-v3.98-317/tmp/15420/a7a3cfacc9/en.wav', source_wav_output='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4/zh-cn.srt', target_wav='E:/win-pyvideotrans-v3.98-317/tmp/15420/a7a3cfacc9/target.wav', target_wav_output='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4/zh-cn.m4a', name='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/8 - Snail modeling/140. Back half main loops.mp4', noextname='140. Back half main loops', basename='140. Back half main loops.mp4', ext='mp4', dirname='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/8 - Snail modeling', shound_del_name=None, translate_type=5, tts_type=8, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='男声.wav', voice_autorate=True, 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=True, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/Udemy - Introduction to 3D Characters Modeling in Blender/_video_out/140. Back half main loops-mp4/140. Back half main loops.mp4', novoice_mp4='E:/win-pyvideotrans-v3.98-317/tmp/15420/a7a3cfacc9/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=4, only_out_mp4=False, recogn2pass=False, output_srt=2, copysrt_rawvideo=False)

=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:E:/win-pyvideotrans-v3.98-317

1 Replies

Floor #1 DeepSeek AI reply at 2 hours ago

这是由于显存或内存不足导致语音识别进程被强制终止。

根据日志，您在使用 faster-whisper(本地) 的 large-v3-turbo 模型进行语音识别时，GPU0 的显存或系统内存不足以处理该任务，导致进程池崩溃。

解决方案：

  1. 更换更小的语音识别模型：这是最直接有效的方法。在软件主界面的“语音识别”下拉菜单中，将模型从 large-v3-turbo 更换为 medium、small 或 base。large-v3 系列模型对显存要求很高。

  2. 调整高级设置以降低资源消耗：在顶部菜单栏选择 工具/选项 -> 高级选项，在“语音识别参数”区域进行如下修改：

    • CUDA数据类型：将 float32 改为 float16 或 int8。
    • 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：确保此项为 false（不勾选）。

  3. 检查并调整GPU任务并发数：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（除非您的单张显卡显存大于20GB）。
    • 如果有多张显卡，可以尝试启用 多显卡模式[重启生效]，并确保显存足够。
  4. 检查文件路径长度：您的视频文件路径 E:/Tutorial/UdemyIntroductionto3DCharactersModelinginBlender/... 非常长。Windows系统对路径长度有限制，过长的路径也可能引发问题。请尝试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。
  5. 验证CUDA环境：虽然错误提示显存不足，但也请确认CUDA环境已正确安装。在CMD中输入 nvidia-smi 查看显卡状态，确保CUDA版本为12.8。

如果以上步骤仍无法解决问题，可能是视频本身较长或复杂，即使使用小模型也超出硬件能力。您可以考虑使用在线语音识别API（如OpenAI、Gemini）来规避本地硬件限制。

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