-
-
-
-
Hi,
I used your pretrained DCCRN, but there are some problem
First, it requires 2 seconds longer signal
And, the output value are NaNs
I tried with sample audio in tests/data/vctk.
And my envir…
-
Hello,
I have a question about SE models. I want to get DCCRN single channel model that has the best pesq value for CHiMe4 dataset but couldn't see it in Hugging Face models page.
Thanks.
-
-
-
I trained dc_crn, and make the mode to "mapping". I remove the argument "--normalize_output_wav true" in "enh.sh", but in stage 7, the output wav is still scale-normalized. But this is not the case in…
-
In dc_crn.py inputs and labels are random tensor.
How could I process sample wav files?
Is it right to change line 305 at dc_crn.py into some kind of wav file read such as sf.read('./noreverb_filei…
-
I would like to ask how to preprocess the data set when the DCCRN model is trained with the wsj0 data set