#5133 TaskCfgVTT(uuid='c84b0881d6', name='C:/Users/56352/Desktop/test.mp4', dirname='C:/Users/56352/Desktop', noextname='test'

67.230* Posted at: 1 day ago

mkl_malloc: failed to allocate memory,Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 207, in faster_whisper
File "videotrans\process\stt_fun.py", line 172, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory
[faster-whisper(本地内置), Google(免费), Edge-TTS(免费)]
Traceback (most recent call last):
File "videotrans\task\only_one.py", line 47, in run
File "videotrans\task\trans_create.py", line 322, in recogn
File "videotrans\recognition\__init__.py", line 190, in run
File "videotrans\recognition\_base.py", line 94, in run
File "videotrans\recognition\_whisper.py", line 37, in _exec
File "videotrans\recognition\_whisper.py", line 120, in _faster
File "videotrans\configure\base.py", line 258, in _new_process
videotrans.configure.excepts.VideoTransError: mkl_malloc: failed to allocate memory,Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 207, in faster_whisper
File "videotrans\process\stt_fun.py", line 172, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory
TaskCfgVTT(uuid='c84b0881d6', name='C:/Users/56352/Desktop/test.mp4', dirname='C:/Users/56352/Desktop', noextname='test', basename='test.mp4', ext='mp4', target_dir='C:/Users/56352/Desktop/测试产品/test-mp4', cache_folder='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22904/c84b0881d6', is_cuda=False, source_language='简体中文', source_language_code='zh-cn', source_sub='C:/Users/56352/Desktop/测试产品/test-mp4/zh-cn.srt', source_wav='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22904/c84b0881d6/zh-cn.wav', source_wav_output='C:/Users/56352/Desktop/测试产品/test-mp4/zh-cn.m4a', target_language='英语', target_language_code='en', target_sub='C:/Users/56352/Desktop/测试产品/test-mp4/en.srt', target_wav='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22904/c84b0881d6/target.wav', target_wav_output='C:/Users/56352/Desktop/测试产品/test-mp4/en.m4a', translate_type=0, tts_type=0, volume='+0%', pitch='+0Hz', voice_rate='+0%', voice_role='Aria(Female/US)', voice_autorate=True, video_autorate=False, remove_silent_mid=False, align_sub_audio=True, detect_language='zh-cn', recogn_type=0, model_name='large-v3-turbo', shibie_audio=None, remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=0, subtitle_language=None, app_mode='biaozhun', subtitles='', targetdir_mp4='C:/Users/56352/Desktop/测试产品/test-mp4/test.mp4', novoice_mp4='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22904/c84b0881d6/novoice.mp4', is_separate=False, embed_bgm=True, instrument=None, vocal='D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612/tmp/22904/c84b0881d6/vocal.wav', clear_cache=True, background_music='', subtitle_type=1, only_out_mp4=True, recogn2pass=False, output_srt=0, copysrt_rawvideo=False, loop_backaudio=1, backaudio_volume=0.8)


=
system:Windows-10-10.0.26200-SP0
version:v4.02
frozen:True
language:zh
root_dir:D:/BaiduNetdiskDownload/win-pyvideotrans-v4.02-0612

1 Replies

这是典型的系统内存不足错误。mkl_malloc: failed to allocate memory 表示在加载 large-v3-turbo 模型时,物理内存(RAM)耗尽,无法为模型分配空间。

原因

  • 你当前未启用 CUDA 加速is_cuda=False),因此依赖 CPU 运行 faster-whisper。
  • large-v3-turbo 模型在 CPU 模式下需要大量 RAM,一般至少需要 16GB 可用内存才能正常加载。如果内存不足(例如被其他程序占用过多),就会触发此错误。

解决方案(按推荐顺序尝试):

  1. 先尝试使用更小的模型:将语音识别模型改为 tinybasesmall,这些模型对内存要求低很多,加载速度快。

    • 在主界面“语音识别渠道”选择 faster-whisper(本地) → 模型下拉改为 tinybase
  2. 释放系统内存:关闭不必要的浏览器标签页、视频/游戏等内存占用程序,重启软件再试。
  3. 如果拥有 NVIDIA 显卡:务必正确安装 CUDA 12.8+ 和 cuDNN 9.x,然后在主界面勾选 CUDA加速。GPU 推理可以显著降低内存压力,同时提速数倍。
  4. 清理路径问题:虽然与该错误无直接关系,但你的输出路径包含“测试产品”中文,建议改为纯英文路径(如 D:\output),避免其他潜在兼容性问题。

如果上述方法仍无效,请提供 logs/ 目录下的最新日志文件或截图底部 30 行报错信息,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. Dondate: ko-fi.com/jianchang512

Related resource