search

jaywalnut310 / vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
https://jaywalnut310.github.io/vits-demo/index.html
MIT License
6.92k stars 1.27k forks source link

VITS paper ? #1

Closed rishikksh20 closed 3 years ago

rishikksh20 commented 3 years ago

@jaywalnut310 I am unable to find the paper on which this repo based on.

jaywalnut310 commented 3 years ago

@rishikksh20 Thanks for you interest! The paper will be uploaded on arxiv after a couple of days (if no problem arises). When it's uploaded, I'll update README and make a link to it. Please wait until then :).

rishikksh20 commented 3 years ago

Great!!!

jaywalnut310 commented 3 years ago

Now the paper is available: https://arxiv.org/abs/2106.06103

rishikksh20 commented 3 years ago

@jaywalnut310 thanks. I set-up collab for LJ-Speech : https://colab.research.google.com/drive/1aNMn2PHDzhQ2nFU5RoWsPSjesDeedm5B?usp=sharing

jaywalnut310 commented 3 years ago

@jaywalnut310 thanks. I set-up collab for LJ-Speech : https://colab.research.google.com/drive/1aNMn2PHDzhQ2nFU5RoWsPSjesDeedm5B?usp=sharing

@rishikksh20 Thans for your amazing work! Is it okay to introduce your collab in README? It would be much grateful, if your sentence of the last line is like "We propose VITS, a Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech."

rishikksh20 commented 3 years ago

Yeah Sure, I have update the collab notebook.

jaywalnut310 commented 3 years ago

@rishikksh20 Based on your work, I made a new notebook including multi speaker examples. Thanks again for your work, and I referred you in README!

SameerSri72 commented 5 months ago

@rishikksh20 sir your colab notebook is not running smoothly due to version mismatch. while installing requirements encounters error in generating package metadata. And !python setup.py build_ext --inplace is not able to create necessary core.cpython file. with my limited understanding I modified certain parts of your notebook and it is working upto "Multi speaker" section. please have a look https://colab.research.google.com/drive/1Sz6OW25WXPIhuEElgAFy77o98YOdhx7a?usp=sharing

if these changes are acceptable then you can modify the notebook for the benefit of everybody. For a newbie like me any feedback/suggestion will mean a lot. FYI @jaywalnut310