#3775 TaskCfgVTT(is_cuda=True, uuid='8cb4b92b38', cache_folder='E:/videotrans/tmp/26908/8cb4b92b38', target_dir='C:/Users/1283

154.36* Posted at: 2 hours ago 👁6

合并阶段出错 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 288, in run
File "videotrans\task\trans_create.py", line 796, in assembling
File "videotrans\task\trans_create.py", line 1258, in _join_video_audio_srt
File "videotrans\task\trans_create.py", line 537, in recogn2pass
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='8cb4b92b38', cache_folder='E:/videotrans/tmp/26908/8cb4b92b38', target_dir='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov', source_language='简体中文', source_language_code='zh-cn', source_sub='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov/zh-cn.srt', source_wav='E:/videotrans/tmp/26908/8cb4b92b38/zh-cn.wav', source_wav_output='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov/zh-cn.m4a', target_language='葡萄牙语', target_language_code='pt', target_sub='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov/pt.srt', target_wav='E:/videotrans/tmp/26908/8cb4b92b38/target.wav', target_wav_output='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov/pt.m4a', name='C:/Users/12834/Desktop/3-24/3月24日/3月24日-11.mov', noextname='3月24日-11', basename='3月24日-11.mov', ext='mov', dirname='C:/Users/12834/Desktop/3-24/3月24日', shound_del_name=None, translate_type=1, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Duarte(Male/PT)', voice_autorate=True, video_autorate=True, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', 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='biaozhun', subtitles='', targetdir_mp4='C:/Users/12834/Desktop/3-24/完成/3月24日-11-mov/3月24日-11.mp4', novoice_mp4='E:/videotrans/tmp/26908/8cb4b92b38/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=False, background_music=None, subtitle_type=1, only_out_mp4=True, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


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

1 Replies

这是由于GPU显存或系统内存不足导致的,特别是在使用大型语音识别模型(如 large-v3-turbo)并开启“二次识别”时,GPU进程池崩溃。

解决方案:

  1. 降低模型规格:在语音识别渠道中,将模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmalllarge-v3-turbo 模型需要大量显存。
  2. 调整高级设置:进入 菜单 -> 工具 -> 高级选项,在“语音识别参数”区域进行以下调整,以降低显存和内存占用:

    • 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:确保此项为关闭状态。
  3. 关闭二次识别:如果当前任务对字幕与配音的精确对齐要求不高,可以在主界面取消勾选“二次识别”选项,以跳过导致本次错误的“合并阶段”的二次语音识别步骤。
  4. 检查并限制GPU任务数:在 菜单 -> 工具 -> 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,除非你的单张显卡显存大于20GB。
  5. 清理缓存并重启:关闭软件,手动删除软件根目录下的 tmp 文件夹内容以释放磁盘空间,然后重新启动软件再尝试处理。

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