Christian Schäfer
Christian Schäfer
Hi, what's the exact schedule you are using? Usually I see a slight drop in the attention score over time, but not too much. Its also questionable whether a higher...
Hi, did you also change the data path in hparams? Because otherwise it would probably mix two datasets. The error message indicates that there is no training file to be...
In this case it seems to me that there is a mismatch of text ids and wav file names, because it is only taking into account files that are matching....
Good point, I will changes the scripts to take into account the hparams setting. I honestly mostly leave the data naming the same and make copies of the dataset if...
Training ForwardTacotron on a dataset comprised of multiple male voices as a single speaker dataset?
Hi, short answer is that the voice is going to be rubbish as the model will average them. I will probably implement a multispeaker version soon. The idea is to...
Training ForwardTacotron on a dataset comprised of multiple male voices as a single speaker dataset?
I think still this makes much more sense if you have the voice conditioning. Do the authors share their model architecture? I suspect they are using some speaker embedding.
Training ForwardTacotron on a dataset comprised of multiple male voices as a single speaker dataset?
Ah very interesting. Could well be tried with this repo then. If there is enough data for each speaker, it could work. Just try it out and throw everything in....
Training ForwardTacotron on a dataset comprised of multiple male voices as a single speaker dataset?
Good luck, lmk how it goes!
Training ForwardTacotron on a dataset comprised of multiple male voices as a single speaker dataset?
The tacotron is only used to extract phoneme durations from the dataset. Once you processed all voices at once you can simply use the latest forward model to fine-tune. You...
Hi, this seems to be a version problem with pytorch and some other library. Did you try to switch to another pytorch version?