#1638 TaskCfg(cache_folder='D:/videotrans/pyvideotrans385/tmp8176/speech2text', target_dir='d:/pyvideo/win-pyvideotrans-v3.85/

112.224* Posted at: 5 hours ago 👁13

语音识别阶段出错:[faster-whisper(本地)] 运行时错误:Traceback (most recent call last):
File "videotrans\process\_overall.py", line 92, in run
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory
:
Traceback (most recent call last):
File "videotrans\task\job.py", line 113, in run
File "videotrans\task\_speech2text.py", line 142, in recogn
File "videotrans\recognition\__init__.py", line 236, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_overall.py", line 199, in _exec
RuntimeError: Traceback (most recent call last):
File "videotrans\process\_overall.py", line 92, in run
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

TaskCfg(cache_folder='D:/videotrans/pyvideotrans385/tmp8176/speech2text', target_dir='d:/pyvideo/win-pyvideotrans-v3.85/output/recogn', remove_noise=False, is_separate=False, detect_language='ja', subtitle_language=None, source_language=None, target_language=None, source_language_code=None, target_language_code=None, source_sub=None, target_sub='d:/pyvideo/win-pyvideotrans-v3.85/output/recogn/1.srt', source_wav=None, source_wav_output=None, target_wav=None, target_wav_output=None, subtitles=None, novoice_mp4=None, noextname='1', shibie_audio='D:/videotrans/pyvideotrans385/tmp8176/speech2text/1-1764172477.7249727.wav', targetdir_mp4=None, instrument=None, vocal=None, back_audio=None, background_music=None, app_mode='biaozhun', subtitle_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role=None, copysrt_rawvideo=False, clear_cache=False, translate_type=None, tts_type=None, recogn_type=0, model_name='large-v3-turbo', split_type=0, voice_autorate=False, video_autorate=False, cuda=False, name='D:/迅雷下载/筛选区/_video_out/1.mp4', basename='1.mp4', ext='mp4', dirname='D:/迅雷下载/筛选区/_video_out', shound_del_name=None, uuid='5836268013', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0)


=
system:Windows-10-10.0.19045-SP0
version:v3.85
frozen:True
language:zh
root_dir:D:/videotrans/pyvideotrans385

1 Replies

这是内存分配失败错误,通常是由于系统内存不足或模型过大导致。请按以下步骤解决:

  1. 更换更小的语音识别模型:在主界面第2行的语音识别设置中,将模型从 large-v3-turbo 改为 mediumsmall
  2. 启用CUDA加速(如有NVIDIA显卡):在主界面第6行勾选"CUDA加速"。
  3. 调整高级设置

    • 在菜单栏选择 工具/选项 -> 高级选项
    • 在"Faster/OpenAI/Whisper语音识别"区域:

      • 将"CUDA数据类型"改为 int8(显存占用最小)
      • 将"识别准确度(beam_size)"改为 1
      • 将"识别准确度(best_of)"改为 1
      • 将"启用上下文感知"设为 False
  4. 使用批量推理模式:在主界面第2行将识别模式从"整体识别"改为"批量推理"。
  5. 关闭其他占用内存的程序:在处理视频时关闭浏览器、游戏等内存密集型应用。

如果以上方法仍无法解决,请提供您的系统内存大小和显卡型号信息。

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.

Donate: https://ko-fi.com/jianchang512

Similar issues already exist

Trending Questions