skol101

Results 47 comments of skol101

Inference with noisy source

Wow, is this really a mystery @yl4579 ?

Inference with noisy source

Here it was reported that added reverb/background noises did help https://github.com/yl4579/StarGANv2-VC/issues/6#issuecomment-1108044051 Maybe the solution is to denoise the input wave before proceeding with inference, so something like Facebook denoiser can...

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

And to generealise well, we need to have multiple discriminators (e.g. 1 per 10 speakers), as discussed in another topic?

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

@yl4579 cheers! How about shared projection as per https://github.com/yl4579/StarGANv2-VC/issues/6#issuecomment-968460007 ? Is it applicable to any-to-many conversion?

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

@thsno02 what vocoder have you used?

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

Interesting, it was reported elsewhere that style encoder is better at VC than mapping network. Also, you haven't fine tuned the vocoder to your dataset?

Any to many vc, how to improve the speech intelligence for arbitrary inputs？

Have you trained them (mapping and style) both or separately?

FileNotFoundError: [Errno 2] No such file or directory: ':/usr/local/cuda:/usr/local/cuda-10.1/bin/nvcc': ':/usr/local/cuda:/usr/local/cuda-10.1/bin/nvcc'

Yep, same problem here. After export CUDA_HOME=/usr/local/cuda , which nvcc can't find nvcc, but setup can run . What gives?

Docker cant find local images on macbook m1

This issue is extremely frustrating. I've created custom builder docker buildx create --name amd64_builder --platform linux/amd64 to compile docker images GCP/AWS. And when I run DOCKER_BUILDKIT=0 docker buildx bake --load...

hop_length not working

Same error here.