#6845 语音识别阶段出错 [faster-whisper(本地)] 出错了,可能内存或显存不足A child process terminated abruptly, the process pool is not usable anymore

103.197.**5 Posted at: 1 hour ago

语音识别阶段出错 [faster-whisper(本地)] 出错了,可能内存或显存不足
A child process terminated abruptly, the process pool is not usable anymore
Traceback (most recent call last):
File "videotrans\configure\_base.py", line 280, in _new_process
File "videotrans\process\signelobj.py", line 81, 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 353, in recogn
File "videotrans\recognition\__init__.py", line 265, 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 294, in _new_process
RuntimeError: 出错了,可能内存或显存不足
A child process terminated abruptly, the process pool is not usable anymore
TaskCfgVTT(is_cuda=True, uuid='b5d4cd0ca2', cache_folder='E:/pyvideotrans-v3.98/tmp/14388/b5d4cd0ca2', target_dir='C:/Users/UserName/Desktop/_video_out/2nv-wav', source_language='简体中文', source_language_code='zh-cn', source_sub='C:/Users/UserName/Desktop/_video_out/2nv-wav/zh-cn.srt', source_wav='E:/pyvideotrans-v3.98/tmp/14388/b5d4cd0ca2/zh-cn.wav', source_wav_output='C:/Users/UserName/Desktop/_video_out/2nv-wav/zh-cn.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='C:/Users/UserName/Desktop/_video_out/2nv-wav/zh-cn.srt', target_wav='E:/pyvideotrans-v3.98/tmp/14388/b5d4cd0ca2/target.wav', target_wav_output='C:/Users/UserName/Desktop/_video_out/2nv-wav/zh-cn.m4a', name='C:/Users/UserName/Desktop/pianduannv/2nv.wav', noextname='2nv', basename='2nv.wav', ext='wav', dirname='C:/Users/UserName/Desktop/pianduannv', shound_del_name=None, translate_type=10, tts_type=1, volume='+10%', pitch='+0Hz', voice_rate='+0%', voice_role='No', voice_autorate=False, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', recogn_type=0, model_name='distil-large-v3.5', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='C:/Users/UserName/Desktop/_video_out/2nv-wav/2nv.mp4', novoice_mp4='E:/pyvideotrans-v3.98/tmp/14388/b5d4cd0ca2/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=1, only_out_mp4=False, recogn2pass=False, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.22621-SP0
version:v3.98
frozen:True
language:zh
root_dir:E:/pyvideotrans-v3.98

1 Replies

#1 DeepSeek reply at 1 hour ago

这是本地 faster-whisper 子进程崩溃导致的 BrokenProcessPool 错误,最常见原因是 CUDA 显存不足,也可能因模型损坏或驱动兼容性问题引发。

请按以下顺序排查处理:

  1. 降低模型尺寸:你当前使用的是 distil-large-v3.5 模型,对显存要求较高。建议到主界面语音识别渠道中将模型改为 smallmedium 再试。
  2. 关闭 GPU 同时任务数:打开菜单 → 工具 → 高级选项 → 通用设置,将 GPU同时任务数 设为 1;若有多张显卡可考虑关闭 多显卡模式
  3. 重启软件:子进程池已不可用,必须完全关闭并重新打开 sp.exe 后再执行。
  4. 检查 CUDA 配置:确认已安装 CUDA 12.8 及 cuDNN 9.11 且环境变量正确。可在 高级选项 → 语音识别参数 中将 计算数据类型 改为 int8float16,并调低 beam_sizebest_of1,关闭 启用上下文感知
  5. 模型文件可能是损坏的不完整:若以上仍失败,删除本地模型目录 E:/pyvideotrans-v3.98/models/models--Systran--faster-distil-whisper-large-v3.5(对应 distil-large-v3.5 的模型)后重新自动下载,或手动下载完整模型覆盖。
  6. 若显存确实不足(如显存小于6G),可暂时关闭CUDA加速,改用CPU处理(速度会慢很多)。

请查阅相关文档:

Thinking...
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.

Dondate via ko-fi.com

Related resource