#6248 语音识别阶段出错:[faster-whisper(本地)] 运行时错误：Traceback (most recent call last): File

2001:da8* Posted at: 5 hours ago

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 45, in run
File "faster_whisper\transcribe.py", line 675, in init
RuntimeError: mkl_malloc: failed to allocate memory
:
Traceback (most recent call last):
File "videotrans\task\job.py", line 107, in run
File "videotrans\task\trans_create.py", line 371, in recogn
File "videotrans\recognition\__init__.py", line 242, 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 45, in run
File "faster_whisper\transcribe.py", line 675, in init
RuntimeError: mkl_malloc: failed to allocate memory

=
system:Windows-10-10.0.26200-SP0
version:v3.84
frozen:True
language:zh
root_dir:E:/win-videotrans-v3.84

Floor #1 DeepSeek reply at 5 hours ago

这是 faster-whisper 在初始化模型时调用底层 MKL 库分配内存失败（mkl_malloc: failed to allocate memory）导致的，核心原因是系统可用内存不足，或识别任务并发数量过高。

关闭其他占用内存的软件，释放物理内存；若软件已连续运行较长时间，建议先完全退出后重新启动，再执行单个视频测试。
降低识别模型大小：将语音识别渠道中的 faster-whisper 模型从 large-v3/medium 改为 small/base/tiny；进入“高级选项 -> 语音识别参数”，将“计算数据类型”改为 int8，可显著减少内存占用。
降低并发占用：进入“高级选项 -> 通用设置”，将“CPU同时任务数”和“GPU同时任务数”都设为 1；若一次翻译多个视频，将“批量翻译视频时每批数量”设为 1。
若以上操作后问题依旧，建议升级到最新版本 v4.08-0802，并使用官方完整包覆盖安装。

#6248 语音识别阶段出错:[faster-whisper(本地)] 运行时错误：Traceback (most recent call last): File

1 Replies

请查阅相关文档：

Post Your Reply

Related resource