#7696 mkl_malloc: failed to allocate memory,Traceback (most recent call last): File

23.177**9 Posted at: 1 hour ago

mkl_malloc: failed to allocate memory,Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 73, in _create_model
File "videotrans\process\stt_faster.py", line 77, in _create_model
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in __ini
......
ecognition\__init__.py", line 121, in run
File "videotrans\recognition\_base.py", line 99, in run
File "videotrans\recognition\_whisper.py", line 41, in _exec
File "videotrans\recognition\_whisper.py", line 138, in _faster
File "videotrans\configure\base.py", line 264, in _new_process
videotrans.configure.excepts.VideoTransError: mkl_malloc: failed to allocate memory,Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "videotrans\process\stt_faster.py", line 84, in faster_whisper
File "videotrans\process\stt_faster.py", line 73, in _create_model
File "videotrans\process\stt_faster.py", line 77, in _create_model
File "videotrans\process\stt_faster.py", line 54, in _create_model
File "faster_whisper\transcribe.py", line 689, in init
RuntimeError: mkl_malloc: failed to allocate memory

cfg=[TaskCfgVTT]当前工作模式: 翻译视频单视频模式
原始输入文件名: C:/Users/24666/Desktop/9.29动漫/video-1.mp4,
输出结果保存到文件夹: C:/Users/24666/Desktop/9.29动漫/_video_out/video-1-mp4,
临时文件夹: D:/ABC/tmp/33480/96938fc217
已选清理已存在
未启用CUDA加速
未选降噪
语音识别:faster-whisper(内置), large-v3-turbo, 发音语言: 简体中文, 断句方式:默认断句
翻译渠道:DeepSeek,原始语言:简体中文,目标语言:英语, 已选发送完整字幕
配音渠道:Edge-TTS(免费), 角色:Steffan(Male/US), 配音语言:英语, 未选二次语音识别
音量:+0%, 语速:+0%, 已选音频加速, 未选视频慢速
字幕: 嵌入软字幕
代理地址:http://127.0.0.1:20799
video_duration_ms=105000

=
system:Windows-10-10.0.22000-SP0
version:v4.14
frozen:True
language:zh_CN
root_dir:D:/ABC

#1 DeepSeek reply at 1 hour ago

核心原因是内存不足或代理设置错误。

报错 mkl_malloc: failed to allocate memory 表示 faster-whisper 模型在加载时无法分配到足够内存，结合你未启用 CUDA 加速（纯 CPU 运行 large-v3-turbo 模型，内存需求很大），这是典型的资源耗尽问题。

请按以下步骤逐一排查：

降低模型尺寸：large-v3-turbo 在纯 CPU 下内存需求很高，请在主界面语音识别模型下拉中改为 small 或 base 模型后重试。
检查代理设置：你的日志显示代理地址为 http://127.0.0.1:20799，如果该代理服务并未运行，或本地模型加载过程被代理干扰，也会引发异常。

请确认该代理端口确实有服务在运行，如不需要代理请清空代理文本框后重试。
减小精度资源占用：进入 菜单 → 工具/选项 → 高级选项 → 语音识别参数，将 计算数据类型 改为 int8（最省内存）。
调低搜索深度：在同一面板，将 识别准确度beam_size 和 best_of 从默认值 5 调低至 1。
关闭多余并发：进入 高级选项 → 通用，将 CPU同时任务数 设为 1，并关闭其他占用内存的程序。
显卡加速（根本解决）：纯 CPU 运行大模型本就极慢且易内存溢出。

如有 NVIDIA 显卡，请安装 CUDA 12.8 + cuDNN 9.11 并在界面勾选 启用CUDA加速。

如按上述操作后仍报错，请提供当前可用物理内存大小及修改后的日志。

#7696 mkl_malloc: failed to allocate memory,Traceback (most recent call last): File

1 Replies

请查阅相关文档：

Post Your Reply

Related resource