#1781 TaskCfg(cache_folder='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355', target_dir='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/

101.71* Posted at: 4 days ago 👁30

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 93, 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 360, in recogn
File "videotrans\recognition\__init__.py", line 243, in run
File "videotrans\recognition\_base.py", line 78, in run
File "videotrans\recognition\_overall.py", line 180, in _exec
RuntimeError: Traceback (most recent call last):
File "videotrans\process\_overall.py", line 93, in run
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

TaskCfg(cache_folder='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355', target_dir='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4', remove_noise=False, is_separate=True, 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='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4/en.srt', target_sub='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4/zh-cn.srt', source_wav='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355/en.wav', source_wav_output='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4/en.m4a', target_wav='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355/target.wav', target_wav_output='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4/zh-cn.m4a', subtitles='', novoice_mp4='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355/novoice.mp4', noextname='How does our Digestive System Work #aumsum #kids #cartoon #science', shibie_audio=None, targetdir_mp4='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/_video_out/How does our Digestive System Work #aumsum #kids #cartoon #science-mp4/How does our Digestive System Work #aumsum #kids #cartoon #science.mp4', instrument='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355/instrument.wav', vocal='I:/fanyi/win-pyvideotrans-v3.87/tmp/18056/26bc513355/vocal.wav', back_audio='', background_music=None, app_mode='biaozhun', subtitle_type=1, volume='+0%', pitch='+0Hz', voice_rate='+2%', voice_role='云健(Male/CN)', copysrt_rawvideo=False, clear_cache=True, translate_type=4, tts_type=0, recogn_type=0, model_name='large-v3-turbo', split_type=0, voice_autorate=False, video_autorate=True, cuda=True, name='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/第三周/How does our Digestive System Work #aumsum #kids #cartoon #science.mp4', basename='How does our Digestive System Work #aumsum #kids #cartoon #science.mp4', ext='mp4', dirname='I:/账号运营工作/BaiduSyncdisk/杂活/奥配音/素材/第三周', shound_del_name=None, uuid='26bc513355', remove_silent_mid=False, align_sub_audio=True, enable_diariz=False, nums_diariz=0, rephrase=2)

=
system:Windows-10-10.0.22621-SP0
version:v3.87
frozen:True
language:zh
root_dir:I:/fanyi/win-pyvideotrans-v3.87

1 Replies

Floor #1 DeepSeek Posted at 4 days ago

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。这通常发生在使用大模型（如 large-v3-turbo）或系统内存本身较小的情况下。

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 medium 或 small。这是最直接有效的方法。
  2. 启用批量推理模式：在主界面第2行“识别模式”中，选择 批量推理 而非 整体识别。此模式会分段处理音频，对内存压力更小。

  3. 调整高级设置（如果仍使用大模型）：

    • 进入 菜单 -> 工具 -> 高级选项。

    • 在“Faster/OpenAI/Whisper 语音识别微调”区域：

      • 将 CUDA数据类型 改为 int8（显存和内存占用最小）。
      • 将 识别准确度 (beam_size) 和 识别准确度 (best_of) 都改为 1。
      • 将 启用上下文感知 设为 False。
  4. 检查并关闭其他占用内存的程序：关闭不必要的浏览器标签、大型软件（如Photoshop、游戏），以释放更多内存。
  5. 检查文件路径：您的视频文件路径包含中文和空格（如 I:/账号运营工作/...）。虽然这不一定是导致内存错误的主因，但为了排除所有潜在问题，强烈建议将视频文件复制到一个纯英文、无空格的短路径下（例如 D:/video/test.mp4）再进行处理。

如果以上步骤仍无法解决，可能是视频过长或系统物理内存严重不足，请考虑升级硬件或使用在线语音识别API（如OpenAI Whisper API）来替代本地模型。

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