Raymond Guo

> > > > 参考这里修改，重新运行会自动下载到C盘，就解决了。 [#26 (comment)](https://github.com/RVC-Boss/GPT-SoVITS/issues/26#issuecomment-1895420620) > > > > > > > > > 我参考这里改了，重新走网络下载，报一样的错误 > > > > > > 我重下之后就好了，或者你降级funasr试试，重下前我也执行了降级。 pip install funasr==0.8.7 pip install modelscope==1.10.0...

> > 我也是一样的问题 funasr 0.8.8 modelscope 1.11.0 > > 和楼上一样用whisper处理了 请问用whisper的话输出格式是whisper的带时间戳的json文件吗

@InsaneGe got same error here, you need to unzip the landscape dataset to the specified directory named "unconditional" which should created by hand.

same error here, 0.0.14-dev0 xformer version did not work for me, (ubuntu 20.04, nvidia t4, pytorch 2.0.0+cu117)

> i am using MacOS with M2. Just modify the function `install_python_dependencies` in `setup.sh` to install xformers > > ``` > "darwin"*) pip install torch==2.0.0 torchvision==0.15.1 \ > -f https://download.pytorch.org/whl/cpu/torch_stable.html...

> 可以在项目路径logs/wzj1/下创建文件：2-name2text-0.txt 后再次尝试一键三连 > > > 请问在点击一键三连时遇到这个错误，FileNotFoundError: [Errno 2] No such file or directory: 'logs/wzj1/2-name2text-0.txt' 然后回继续报错找不到2-name2text-1.txt'

不过确实，每报一个No such file就手动创建一个也是可以解决的。。。

@RowenaHe same problem here, did you mean fix it by something like this?: ``` def noise_images(self, x, t): sqrt_alpha_hat = torch.sqrt(self.alpha_hat[t])[:, None, None, None] sqrt_one_minus_alpha_hat = torch.sqrt(1 - self.alpha_hat[t])[:, None,...

``` No face detected in this image███████▉ | 73/520 [00:17

I tried the same video on google collab , the result is ok, and there is no "No face detected in this image" log, I think on my own machine,...