#4800 TaskCfg(cache_folder='D:/pyvideotrans/tmp/26892/2328c1bbfc', target_dir='D:/Downloads/_video_out/AEDS-152_restored-mp4',

2409:8a6a* Posted at: 4 hours ago

语音识别阶段出错 [faster-whisper(本地)] Traceback (most recent call last):
File "videotrans\process\_overall.py", line 163, in run
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: CUDA failed with error out of memory

Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\trans_create.py", line 365, in recogn
File "videotrans\recognition\__init__.py", line 245, in run
File "videotrans\recognition\_base.py", line 80, in run
File "videotrans\recognition\_overall.py", line 182, in _exec
RuntimeError: Traceback (most recent call last):
File "videotrans\process\_overall.py", line 163, in run
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: CUDA failed with error out of memory

TaskCfg(cache_folder='D:/pyvideotrans/tmp/26892/2328c1bbfc', target_dir='D:/Downloads/_video_out/AEDS-152_restored-mp4', remove_noise=False, is_separate=False, detect_language='ja', subtitle_language=None, source_language='日语', target_language='日语', source_language_code='ja', target_language_code='ja', source_sub='D:/Downloads/_video_out/AEDS-152_restored-mp4/ja.srt', target_sub='D:/Downloads/_video_out/AEDS-152_restored-mp4/ja.srt', source_wav='D:/pyvideotrans/tmp/26892/2328c1bbfc/ja.wav', source_wav_output='D:/Downloads/_video_out/AEDS-152_restored-mp4/ja.m4a', target_wav='D:/pyvideotrans/tmp/26892/2328c1bbfc/target.wav', target_wav_output='D:/Downloads/_video_out/AEDS-152_restored-mp4/ja.m4a', subtitles='', novoice_mp4='D:/pyvideotrans/tmp/26892/2328c1bbfc/novoice.mp4', noextname='AEDS-152_restored', shibie_audio=None, targetdir_mp4='D:/Downloads/_video_out/AEDS-152_restored-mp4/AEDS-152_restored.mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='tiqu', subtitle_type=0, volume='+100%', pitch='+0Hz', voice_rate='+0%', voice_role='No', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=0, model_name='large-v3', split_type=0, voice_autorate=False, video_autorate=False, cuda=True, name='D:/Downloads/AEDS-152_restored.mp4', basename='AEDS-152_restored.mp4', ext='mp4', dirname='D:/Downloads', shound_del_name=None, uuid='2328c1bbfc', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=True)


=
system:Windows-10-10.0.26200-SP0
version:v3.92
frozen:True
language:zh
root_dir:D:/pyvideotrans

1 Replies

这是显存不足导致的错误。您当前使用的模型是 large-v3,且启用了 CUDA 加速,但显存不足以加载该模型。

解决方法(按推荐顺序尝试):

  1. 更换为更小的模型
    在主界面识别渠道中选择 mediumsmallbase 模型(large-v3 至少需要 8G 显存)。
  2. 调整高级选项
    打开 菜单 → 工具/选项 → 高级选项 → 语音识别参数,进行如下修改以降低显存占用:

    • CUDA 数据类型 → 改为 float16int8
    • beam_size → 改为 1
    • best_of → 改为 1
    • 上下文 → 改为 false
  3. 确认显存占用
    关闭其他占用显卡的程序(如浏览器、游戏),确保显存空闲可用。
  4. 若仍有问题
    可暂时取消勾选主界面的 CUDA加速,使用 CPU 模式(速度会明显变慢,但可绕开显存限制)。

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