#854 videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'tts failed', 'Exception':

*345:2d77* Posted at: 2 hours ago 👁5

GPT-SoVITS error-1:{'message': 'tts failed', 'Exception': "[ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Slice node. Name:'Slice_12' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device"} :

Traceback (most recent call last):

File "videotrans\util\ListenVoice.py", line 18, in run

File "videotrans\tts\__init__.py", line 266, in run

File "videotrans\tts\_base.py", line 182, in run

File "videotrans\tts\_gptsovits.py", line 115, in _item_task

File "tenacity\__init__.py", line 338, in wrapped_f

File "tenacity\__init__.py", line 477, in __call__

File "tenacity\__init__.py", line 378, in iter

File "tenacity\__init__.py", line 400, in

File "concurrent\futures\_base.py", line 439, in result

File "concurrent\futures\_base.py", line 391, in __get_result

File "tenacity\__init__.py", line 480, in __call__

File "videotrans\tts\_gptsovits.py", line 99, in _run

videotrans.configure._except.StopRetry: GPT-SoVITS error-1:{'message': 'tts failed', 'Exception': "[ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Slice node. Name:'Slice_12' Status Message: CUDA error cudaErrorNoKernelImageForDevice:no kernel image is available for execution on the device"}

=====

Windows-10-10.0.19045-SP0

version:v3.81

frozen:True

language:zh

1 Replies

本条内容由 DeepSeek 回复
这个问题是由于在使用GPT-SoVITS语音合成时CUDA兼容性错误导致的。具体错误信息"cudaErrorNoKernelImageForDevice"表明您的显卡驱动或CUDA版本与GPT-SoVITS模型不兼容。

解决方案:

1. 更新NVIDIA显卡驱动:前往NVIDIA官网下载并安装最新的显卡驱动程序。

2. 检查CUDA兼容性

  • 在命令行执行 nvidia-smi 查看右上角的CUDA Version
  • 如果显示低于12.x,需要安装CUDA 12.x版本

3. 临时解决方案

  • 在pyVideoTrans的TTS设置中,暂时切换到其他配音渠道,如edge-TTS或Azure TTS
  • 或者取消选中"使用CUDA加速"选项(如果GPT-SoVITS设置中有此选项)

4. 如果显卡过于陈旧

  • 如果您的显卡无法支持CUDA 12.x,建议使用CPU模式运行GPT-SoVITS(如果支持),或者改用其他不需要高版本CUDA的TTS渠道

这个问题与显卡硬件和驱动环境相关,不是pyVideoTrans软件本身的bug。建议先更新驱动,如果问题仍然存在,可以考虑使用其他配音渠道。

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