skol101

Results 47 comments of skol101

Microk8s 1.18 Change default host path storage location

Is there a way to change not only the path but actually type of storage? Because hostPath isn't support by Velero backup.

Can it transfer RFU between different utterances?

@flagman how did you manage to prepare your custom demo.pkl?

Does it will work on unseen data also? will it be able to convert voice of unseen speaker with different content than that of data in training, will we obtain the disentanglement?

@auspicious3000 could you explain what you mean by 'training it the same way as AutoVC"? Repeat all steps from here https://github.com/auspicious3000/autovc#2train-model ? Or change make_metadata.py in SpeechSplit to embed speaker...

Does it will work on unseen data also? will it be able to convert voice of unseen speaker with different content than that of data in training, will we obtain the disentanglement?

I did that -- used make_metadata.py from AutoVC. Now I have removed validation part from the solver.py in this repo, because there's nothing to validate it against (as in solver_encoder.py...

Does it will work on unseen data also? will it be able to convert voice of unseen speaker with different content than that of data in training, will we obtain the disentanglement?

I had to remove validation part because I couldn’t figure out yet how to create my validatation pkl  file yet based on vctk plus my custom voices. On 7 Feb...

Inference with noisy source

> The normalization may have possibly amplified the noises slightly, yet the point of log mel spec is actually the opposite: it tries to emphasize the speech instead of the...

Inference with noisy source

I see, because I thought reverb and noise should be added right in StyleEncoder as per https://github.com/yl4579/StarGANv2-VC/issues/6#issuecomment-1103393827

Inference with noisy source

> @Charlottecuc I'm sorry for the late reply because this issue was closed and I didn't get any notification. Not sure if it has been resolved, but what I meant...

Inference with noisy source

@yl4579 I'm either doing something wrong or adding reverbs and background noises does nothing. When the source (like VCTK p303_013.wav) has breathing, the converted speech has distortions. Maybe the issue...

Inference with noisy source

@Charlottecuc this issue should be reopened to discuss further.