simplify123
simplify123
我昨天部署了rtx5090d显卡,测试了一下制作视频界面那个文本合成声音,点击试听按钮后,确实有沙哑的声音,2080ti的显卡就没这个问题,怀疑是fish-speech导致的,建议官方团队更换为cosyvoice2,效果很好,默认参数就效果很好了 Describe the bug The RTX 5090 GPU has been deployed with guiji2025/fish-speech-5090 and guiji2025/heygem.ai-5090. It can be used, but when synthesizing text into speech, all the voices become hoarse....
我的是从2080显卡今天换成5090d显卡后,这个数字人没办法用了,提示cuda内核错误,怎么解决?你是怎么跑起来的? `========== == CUDA == ========== CUDA Version 12.1.1 Container image Copyright (c) 2016-2023, NVIDIA CORPORATION & AFFILIATES. All rights reserved. This container image and its contents are governed by...
安装最新版docker desktop没有问题,可以正常运行
 I reinstalled the latest version of the Windows 11 operating system, and then installed dependencies such as Python 3.11 and Node.js. Now it can run. Although it can run...
支持,要装12.8版本的cuda https://developer.nvidia.com/cuda-toolkit-archive https://mirrors.aliyun.com/pytorch-wheels/cu128/ pip install torch-2.7.0+cu128-cp310-cp310-win_amd64.whl pip install torchaudio-2.7.0+cu128-cp310-cp310-win_amd64.whl pip install torchvision-0.22.0+cu128-cp310-cp310-win_amd64.whl 安装完检测命令 python -c "import torch; print(torch.cuda.is_available())" nvcc --version python -c "import torch; print(torch.cuda.get_device_capability(0))" python -c "import torch; print(torch.__version__)"...