CaraDuf

That's really weird. I restarted the computer for another reason and now it keeps the 87 / 87 datapoints (without touching anything to the dataset). I may have screwed up...

Ok thank you. So should I change the learning rate in the fine tuning script or it already takes the 1/10 factor into account ?

I looked at the spectrograms and the tips are moving from left to right but the horizontal stripes are there. I haven't looked at the losses, I'll tell you. I...

To answer your previous questions the L1 loss, Glow loss, and spectrogram (before or after I don't remember for sure) look like the following :    L1 loss...

@thoraxe the loss images are from wandb. You have to set up an account and then pass the parameter--wandb

Quick feedback from my side. After pausing the cloning for one week and restarting the computer, it works great (v2.5). I will try to improve the dataset with adobe api...

Ok thanks for your reply. Now I have to learn what "normalizing flows" means (specially what a flow is in TTS) 😉.

Did you try https://github.com/DigitalPhonetics/IMS-Toucan/issues/88 ?

Actually I do believe you already solved all that in v2.5 (so sorry to ask a "backward" question but v2.4 works better for me as voice similarity is concerned). Would...

Fine tuning (6k steps overall) Meta on Siwis dataset and then finetuning (6k steps overall) the resulting model (Siwis) on my dataset gave better results but not perfect. "pin" (pine...