#7233 翻译字幕阶段出错 [M2M100(内置)] parallel_for failed: cudaErrorNoKernelImageForDevice: no kernel image is available for execution o

60.220**0 Posted at: 1 hour ago

翻译字幕阶段出错 [M2M100(内置)] parallel_for failed: cudaErrorNoKernelImageForDevice: no kernel image is available for execution on the device
Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 137, in process_task

File "videotrans\task\translate_srt.py", line 51, in trans

File "videotrans\translator\_runner.py", line 67, in run

File "videotrans\translator\_base.py", line 67, in run

File "videotrans\translator\_base.py", line 105, in _run_text

File "videotrans\translator\_m2m100.py", line 58, in _item_task

RuntimeError: parallel_for failed: cudaErrorNoKernelImageForDevice: no kernel image is available for execution on the device
[TranslateSrt]翻译字幕: OutputFormat=单语字幕
[TaskCfgSTS]
原始输入文件名: E:/AE/After Effects Guru/01 After Effects CC Essential Training(核心培训)/122431_00_02_3D15_files.srt,
输出结果保存到文件夹: D:/win-pyvideotrans-v4.12-0912_20260913_140223/output/translate
翻译渠道:M2M100(内置),原始语言:auto,目标语言:en, 已选 发送完整字幕
代理地址:http://127.0.0.1:2080


=
system:Windows-10-10.0.19045-SP0
version:v4.12
frozen:True
language:zh_CN
root_dir:D:/win-pyvideotrans-v4.12-0912_20260913_140223

1 Replies

#1 DeepSeek reply at 1 hour ago

这是由于您使用的显卡不支持 M2M100 模型所依赖的 CUDA 计算架构(显卡算力过低或型号过老),导致 CUDA 内核无法在该设备上执行。

解决方案:

  1. 改用其他翻译渠道:M2M100 作为本地翻译模型对显卡 CUDA 算力有硬性要求。建议在 翻译字幕 的翻译渠道下拉框中,改用 DeepSeekGoogle(免费) 等云翻译渠道,或在主界面选择其他翻译渠道。国内推荐使用 DeepSeek(效果更好,价格极低)。
  2. 无法通过 M2M100 满足该显卡:该报错属于显卡硬件与 CUDA 内核不兼容,通常无法通过软件设置绕过。

请查阅相关文档:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
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 via ko-fi.com

Related resource