LazyNam

ffmpeg is all you need, i meet the same question in other projects, you can try conda install ffmpeg.

> when you used the DNS-Challenge dataset, did you use the shell file 'download-dns-challenge-4.sh ' to download the data?

> > > > > > > > > when you used the DNS-Challenge dataset, did you use the shell file 'download-dns-challenge-4.sh ' to download the data? > > ...

 I run 2 times, and the enhanced_0194 is null.

I have checked before, there is no thing in enhanced_0194,   My GPU is busy with other task, may be there is no calculate resource to deal with it?...

> Maybe I know where your bug is. The _dataset.path_ refers to a directory of files, not to a specific file. Can you try changing **testdata/input_data/1.wav** to **testdata/input_data**? The same...

你好，请问解决了吗，我目前也在研究基于DTLN的AEC和NS，也希望部署在这一款芯片上面。

> 我试了下非stateful的onnx模型是可以转的 带stateful的就不行了 请问你解决了吗，nonstateful是不能流式的呜呜呜

> @nihui 大佬，麻烦帮忙看一下 > gdb 调试 信息如下， 使用 `cmake -DCMAKE_BUILD_TYPE=Debug` 编译的，但是好像堆栈还是不完整 > > ``` > Type "apropos word" to search for commands related to "word"... > Reading symbols from /home/yangjie/pnnx/pnnx...done....

> If I want to train my own dataset, what should the structure of the dataset be, and should the names of the files in the clean and noise folders...