Air
Air
@sureshdagooglecom So i'm trying to take the landmarks generated by the mediapipe pose model to my Three.js avatar! But it seems like the coodinate systems are different! I was wondering...
same here!!
The thing that I would do is to use the pretrained models that work good for english and then finetune on 12 minutes of your voice! You just have to...
https://github.com/CorentinJ/Real-Time-Voice-Cloning/issues/819#issue-970736011 I used this ussue to preprocess the Mozilla Common voice dataset!
@raccoonML I was wondering if you changed the symbols.py for swedish! Because I have to change che _characters for italian but it gives me error: size mismatch for encoder.embedding.weight: copying...
@raccoonML Hi! Yes I started retraining the synthétiser, I was wondering how you felt with NUMBERS because I know there are libraries that convert digits to English numbers but not...
@raccoonML Thank you! yes one idea was to then translate! :)
@raccoonML Sorry for bothering, When retraining the synthetizer I also need to re do the preprocessing of the dataset with the new symbols right? Because I retrained on and older...
@LinkleZe probably the synthetiser has not learnt the attention, check the attention plots.
Thank you I solved, I had a typo in the script!