Steve Tang/Yuwu Tang

Results 12 issues of Steve Tang/Yuwu Tang

(aligner) D:\code\vits-main\monotonic_align>python setup.py build_ext --inplace running build_ext building 'monotonic_align.core' extension C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.32.31326\bin\HostX86\x86\cl.exe /c /nologo /Ox /W3 /GL /DNDEBUG /MD -IC:\Users\h\.conda\envs\aligner\lib\site-packages\numpy\core\include -IC:\Users\h\.conda\envs\aligner\include -IC:\Users\h\.conda\envs\aligner\include "-IC:\Program Files\Microsoft Visual Studio\2022\Community\VC\Tools\MSVC\14.32.31326\ATLMFC\include" "-IC:\Program Files\Microsoft...

we got problems when extracting visual data, the results we got is all 0 of IEMOCAP. We found it works when other videos but error when IEMOCAP. We tried download...

my config: n_mel=128,n_fft=2048,n_hop=256,sr=16000 it takes about 20 second for getting melspectrogram from 8 second long wav file!!! Is it normal for this code?

How can i get the pretrained_teacher model by myself instead of using the ones u provided?

We cannot reproduce the results about TAPT, and our pretraining loss is ''nan'' when running ''FT-w2v2-ser-main\run_baseline_continueFT.py''. Can you help us solve this issue?

the inputs of twice pcen function are the same, do i need run it twice? And which output i should need? the first time output mels or the second?