#4003 TaskCfgVTT(is_cuda=True, uuid='8f2efd781a', cache_folder='G:/VideoTrans/tmp/14524/8f2efd781a', target_dir='D:/Bl tuatrio

119.123* Posted at: 9 hours ago 👁17

语音识别阶段出错 [faster-whisper(本地)] 出错了,可能内存或显存不足 Model:large-v3-turbo 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 292, 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 303, in _new_process
RuntimeError: 出错了,可能内存或显存不足 Model:large-v3-turbo 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='8f2efd781a', cache_folder='G:/VideoTrans/tmp/14524/8f2efd781a', target_dir='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4', source_language='英语', source_language_code='en', source_sub='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4/en.srt', source_wav='G:/VideoTrans/tmp/14524/8f2efd781a/en.wav', source_wav_output='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4/zh-cn.srt', target_wav='G:/VideoTrans/tmp/14524/8f2efd781a/target.wav', target_wav_output='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4/zh-cn.m4a', name='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/137. 07_02 How to get Free Music & Sound FX.mp4', noextname='137. 07_02 How to get Free Music & Sound FX', basename='137. 07_02 How to get Free Music & Sound FX.mp4', ext='mp4', dirname='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production', shound_del_name=None, translate_type=0, tts_type=2, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='001.wav', voice_autorate=False, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='en', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=True, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/Bl tuatriol/A Z Guide/7 - Chapter 7 Video Editing & Post Production/07/137. 07_02 How to get Free Music & Sound FX-mp4/137. 07_02 How to get Free Music & Sound FX.mp4', novoice_mp4='G:/VideoTrans/tmp/14524/8f2efd781a/novoice.mp4', is_separate=True, embed_bgm=True, instrument='G:/VideoTrans/tmp/14524/8f2efd781a/instrument.wav', vocal='G:/VideoTrans/tmp/14524/8f2efd781a/vocal.wav', back_audio='', clear_cache=False, background_music=None, subtitle_type=1, only_out_mp4=False, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:G:/VideoTrans

1 Replies

这是由于显存或内存不足导致 faster-whisperlarge-v3-turbo 模型加载失败。

解决方案:

  1. 使用更小的模型:在语音识别渠道的下拉菜单中,将模型从 large-v3-turbo 更换为 mediumsmallbaselarge-v3large-v3-turbo 模型对显存要求较高(建议10GB以上)。
  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)。请在主界面右上角取消勾选 二次识别 选项。同时翻译多个视频时,二次识别会显著增加显存需求。
  4. 检查文件路径:您的视频文件路径和名称较长且包含空格(如 137. 07_02 How to get Free Music & Sound FX.mp4)。请将视频文件重命名为简短英文名(如 video.mp4),并移动到浅层目录(如 D:\video)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