Steve Korshakov
Steve Korshakov
Hey! What for? it is trivial to reproduce using scripts in this repo!
Try to install 2x version, this should work. I am in the process of moving training to librilight instead of mixture of different datasets
In my experiments loss doesn't change at all and stuck ~`0.3`, but i can observe the quality change and it improves and improves the longer i train, the longest i...
I have updated all code in eval notebook, also published how to use instructions
Style tokens (which are in fact just normalised pitch) improved emotional prosody a lot. Some of my notebooks has an example of inference without style tokens (I am training 10%...
It is normalized during training, this numbers are from voicebox paper, but i feel for my data they should be different, but i am not careful enough yet. `voice_x.pt` is...
@zvorinji hey, i am not convinced that Whisper has anything useful, i tried in the past to use it's latent outputs to predict presence of the voice, but it turns...
There is a simple script that created built-in voices: https://github.com/ex3ndr/supervoice/blob/master/generate_voices.py You can try to use similar script to create a new voice
I just haven't found a good phonemizer compatible to specific IPA subset that main network is trained on. I tried to use espeak, but it's phonemes are different from montreal...
I did not, you think this would improve something? I never need to fit tokens to a specific timeframe in my setup