#4407 TaskCfgVTT(is_cuda=True, uuid='59ede03afb', cache_folder='C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329/tmp/14248/59e

27.207* Posted at: 1 hour ago 👁8

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 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 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='59ede03afb', cache_folder='C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329/tmp/14248/59ede03afb', target_dir='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4', source_language='英语', source_language_code='en', source_sub='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4/en.srt', source_wav='C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329/tmp/14248/59ede03afb/en.wav', source_wav_output='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4/zh-cn.srt', target_wav='C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329/tmp/14248/59ede03afb/target.wav', target_wav_output='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4/zh-cn.m4a', name='D:/video-in/康复评估/Basic Ankle & Foot Assessment/3 - Resisted Isometric Testing (Ankle⧸Foot).mp4', noextname='3 - Resisted Isometric Testing (Ankle⧸Foot)', basename='3 - Resisted Isometric Testing (Ankle⧸Foot).mp4', ext='mp4', dirname='D:/video-in/康复评估/Basic Ankle & Foot Assessment', shound_del_name=None, translate_type=12, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Yunyang(Male/CN)', 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=1, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/video-in/康复评估/Basic Ankle & Foot Assessment/_video_out/3 - Resisted Isometric Testing (Ankle⧸Foot)-mp4/3 - Resisted Isometric Testing (Ankle⧸Foot).mp4', novoice_mp4='C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329/tmp/14248/59ede03afb/novoice.mp4', is_separate=False, instrument=None, vocal=None, back_audio='', clear_cache=True, background_music=None, subtitle_type=0, only_out_mp4=True, recogn2pass=True, output_srt=0, copysrt_rawvideo=False)


=
system:Windows-10-10.0.26200-SP0
version:v3.98
frozen:True
language:zh
root_dir:C:/Users/DELL/Desktop/win-pyvideotrans-v3.98-329

1 Replies

错误原因:显存不足。模型 large-v3-turbo 在开启 CUDA 且同时执行“二次识别”时,显存占用过高导致进程崩溃。

解决方案(按推荐顺序):

  1. 关闭“二次识别”:在主界面右上角取消勾选“二次识别”,然后重试。
  2. 更换更小的模型:将语音识别模型从 large-v3-turbo 改为 mediumsmall(可在模型下拉列表中选择)。
  3. 调整高级选项降低显存占用:进入 菜单 → 工具/选项 → 高级选项,将:

    • CUDA数据类型 改为 float16int8
    • beam_size 改为 1
    • best_of 改为 1
    • 启用上下文感知 改为 false
  4. 若仍不成功,尝试在高级选项中勾选 Whisper预分割音频,可进一步降低单次显存消耗。

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