#2181 TaskCfg(cache_folder='D:/BaiduNetdiskDownload/tmp/17900/b727550e9f', target_dir='C:/Users/liu/Videos/4K Video Downloader

205.185* Posted at: 23 hours ago 👁15

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: mkl_malloc: failed to allocate 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: mkl_malloc: failed to allocate memory

TaskCfg(cache_folder='D:/BaiduNetdiskDownload/tmp/17900/b727550e9f', target_dir='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4', remove_noise=False, is_separate=False, detect_language='en', subtitle_language=None, source_language='英语', target_language='简体中文', source_language_code='en', target_language_code='zh-cn', source_sub='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4/en.srt', target_sub='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4/zh-cn.srt', source_wav='D:/BaiduNetdiskDownload/tmp/17900/b727550e9f/en.wav', source_wav_output='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4/en.m4a', target_wav='D:/BaiduNetdiskDownload/tmp/17900/b727550e9f/target.wav', target_wav_output='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4/zh-cn.m4a', subtitles='', novoice_mp4='D:/BaiduNetdiskDownload/tmp/17900/b727550e9f/novoice.mp4', noextname='Super compact na multishot. Call or text 09255679062.', shibie_audio=None, targetdir_mp4='C:/Users/liu/Videos/4K Video Downloader+/_video_out/Super compact na multishot. Call or text 09255679062.-mp4/Super compact na multishot. Call or text 09255679062..mp4', instrument=None, vocal=None, back_audio='', background_music=None, app_mode='biaozhun', subtitle_type=1, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Yunyang(Male/CN)', copysrt_rawvideo=False, clear_cache=False, translate_type=0, tts_type=0, recogn_type=0, model_name='large-v3-turbo', split_type=0, voice_autorate=True, video_autorate=False, cuda=False, name='C:/Users/liu/Videos/4K Video Downloader+/Super compact na multishot. Call or text 09255679062..mp4', basename='Super compact na multishot. Call or text 09255679062..mp4', ext='mp4', dirname='C:/Users/liu/Videos/4K Video Downloader+', shound_del_name=None, uuid='b727550e9f', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=0, only_out_mp4=False)


=
system:Windows-10-10.0.19045-SP0
version:v3.91
frozen:True
language:zh
root_dir:D:/BaiduNetdiskDownload

1 Replies

错误 mkl_malloc: failed to allocate memory 表明系统内存(RAM)不足,无法加载 faster-whisper 模型。请按以下步骤解决:

  1. 降低模型大小:在主界面第2行“语音识别”中,将模型从 large-v3-turbo 更换为更小的模型,例如 mediumsmall。这是最直接有效的方法。
  2. 优化内存使用

    • 关闭其他占用大量内存的软件(如浏览器、大型游戏、其他AI软件)。
    • 如果可能,增加系统的虚拟内存(页面文件)大小。
  3. 调整识别模式:在主界面第2行,将识别模式从 整体识别 切换为 批量推理。后者按时间切片处理,对内存峰值要求更低。
  4. 检查高级设置:在菜单栏选择 工具/选项 -> 高级选项,确保 CUDA加速 未被勾选(因为错误提示是系统内存问题,而非显存)。同时,可以尝试将 CUDA数据类型 改为 int8(如果后续使用GPU),但这主要解决显存问题。

如果以上步骤仍无法解决,请提供您电脑的物理内存(RAM)大小,以便进一步分析。

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

Trending Questions