#3747 TaskCfgVTT(is_cuda=True, uuid='53d4f0b912', cache_folder='C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317/tmp/24608/53

220.202* Posted at: 2 hours 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 [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 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='53d4f0b912', cache_folder='C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317/tmp/24608/53d4f0b912', target_dir='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4', source_language='英语', source_language_code='en', source_sub='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4/en.srt', source_wav='C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317/tmp/24608/53d4f0b912/en.wav', source_wav_output='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4/en.m4a', target_language='简体中文', target_language_code='zh-cn', target_sub='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4/zh-cn.srt', target_wav='C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317/tmp/24608/53d4f0b912/target.wav', target_wav_output='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4/zh-cn.m4a', name='D:/下载/新建文件夹/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p.mp4', noextname='divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p', basename='divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p.mp4', ext='mp4', dirname='D:/下载/新建文件夹', shound_del_name=None, translate_type=8, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='No', 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=False, enable_diariz=False, nums_diariz=0, rephrase=1, fix_punc=False, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='D:/aa/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p-mp4/divine-hospitality-sif-s-embrace-dezmall-4k60fps_2160p.mp4', novoice_mp4='C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317/tmp/24608/53d4f0b912/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-10-10.0.26200-SP0
version:v3.98
frozen:True
language:zh
root_dir:C:/Users/wang1/Desktop/win-pyvideotrans-v3.98-317

1 Replies

这是由于显存或内存不足导致的。在使用 faster-whisper(本地)large-v3-turbo 模型进行语音识别时,GPU 进程因资源耗尽而崩溃。

请按以下步骤解决:

  1. 更换更小的语音识别模型:在主界面的语音识别渠道下拉菜单中,将模型从 large-v3-turbo 更换为 mediumsmallbaselarge-v3 系列模型需要大量显存,large-v3-turbo 同样如此。
  2. 调整高级设置以降低资源消耗:点击 菜单 -> 工具 -> 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 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:确保此项为 false(未勾选)。
  3. 检查并限制GPU任务并发:在“高级选项”的“通用设置”区域,确保 GPU同时任务数[重启生效] 设置为 1(除非您的单卡显存大于20GB)。
  4. 确保CUDA环境正确:虽然错误提示来自GPU0,但仍需确认CUDA版本为12.8且已正确安装。在CMD中输入 nvcc -Vnvidia-smi 进行验证。
  5. 关闭其他占用显存的程序:在处理视频前,关闭不必要的游戏、浏览器或其他AI应用,以释放显存。

如果上述步骤后问题依旧,可能是视频过长或系统内存不足,请尝试使用更小的模型(如 tiny)或使用在线语音识别API(如OpenAI)替代本地模型。

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