#538 {'code': 6, 'msg': 'CUDA error: no kernel image is available for execution on the device\nCUDA kernel errors might be as

14.145* Posted at: 1 month ago 👁215

{'code': 6, 'msg': 'CUDA error: no kernel image is available for execution on the device\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1.\nCompile with TORCH_USE_CUDA_DSA to enable device-side assertions.\n'}

=====

Windows-10-10.0.19045-SP0

version:v3.80

frozen:True

language:zh

12 Replies

Floor #1 129.159* Posted at 1 month ago

Admin

对应使用的是某个tts渠道、语音识别渠道？那个软件的配置cuda环境有问题

Floor #2 14.145* Posted at 1 month ago

image

克降音色

image

Floor #3 39.87* Posted at 1 month ago

Admin

clone-voice预打包版不支持cuda13，使用cuda12，或者源码方式部署 clone-voice

Floor #4 14.145* Posted at 1 month ago

好的我会继续尝试感谢

Floor #5 14.145* Posted at 1 month ago

image

我已经弄成12.6了 但还是会有那个问题 是还有哪些地方要改吗image

Floor #6 39.87* Posted at 1 month ago

Admin

clone-voice预打包版不支持 50x系显卡，是50显卡吗？

可尝试源码部署

Floor #7 74.63* Posted at 1 month ago

是50显卡

我单独用这个也无法用声音转声音!

image

image

Floor #8 74.63* Posted at 1 month ago

是否有其它的方式不用源码部署的，我只想翻译视频中的人的英文成中文然后用他自己的音色，同时能支持50系显卡

Floor #9 39.87* Posted at 1 month ago

Admin

改为 cpu试试

image

如果还不行，可以试试 F5-TTS ，index-tts等

Floor #10 14.145* Posted at 1 month ago

还是不行，另外我尝试在使用这个命令的时候python -m venv myenv 目录下没有创建myen文件夹

Floor #11 14.145* Posted at 1 month ago

image

已经安装 了

Floor #12 14.145* Posted at 1 month ago

image

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

Similar issues already exist

Trending Questions