Issues
- 0
Using knn-vc for audio streams
#39 opened by vitreo12 - 5
Cannot download model.
#42 opened by sai4july - 1
Using a Generator Network Before the Vocoder
#41 opened by saeedzou - 0
onnx support
#40 opened by zdj97 - 4
- 1
- 2
Request
#36 opened by dillfrescott - 1
Question about the Used Hardware
#37 opened by CCMaure - 0
extend to other SSL model features
#22 opened - 1
How to plug-in new finetuned HiFiGAN?
#34 opened by youssefabdelm - 2
Some question about features KNN
#35 opened by huutuongtu - 4
Will this work with 44100hz audio?
#23 opened by dillfrescott - 6
- 2
Some questions about implementation
#31 opened by TOGA101 - 3
- 2
Matching pool empty
#32 opened by asusdisciple - 2
Using another batch size in training
#30 opened by asusdisciple - 3
- 2
- 2
Size mismatch error
#25 opened by JBloodless - 2
Error in quickstart
#24 opened by lesept777 - 16
Training HiFiGAN on higher quality data
#11 opened by gaurangbharti1 - 2
Considering context around source features
#19 opened by wilson97 - 2
Choice for k
#17 opened by tebin - 4
prematch_dataset run very slow
#15 opened by fangg2000 - 2
prematch argument
#16 opened by d2sys - 1
Torch Hub CPU inference support
#14 opened by skyler14 - 2
Question about WavLM layer choice
#13 opened by space-pope - 1
out_wav is a wav file?
#12 opened by fangg2000 - 1
Output is a bit shaky, how to fix that?
#9 opened by Souvic - 1
WavLM Base+ over Large?
#10 opened by Pathos0925 - 1
- 1
Discriminator checkpoint
#8 opened by hippotabek - 2
An error when loading models
#6 opened by chienlinhuang1116 - 2
torchaudio version
#7 opened by Blakey-Gavin - 1
bigvgan as vocoder
#3 opened by eschmidbauer - 0
Link to paper
#1 opened by Ashraf-Ali-aa - 0
An error when check input type
#2 opened by yzmyyff