metadata

license: apache-2.0
language:
  - en
tags:
  - ai
  - rvc
  - vc
  - voice-cloning
  - applio
  - titan
  - pretrained

TITAN: A Robust Pretrained Model for Retrieval-based Voice Conversion Training

Overview

TITAN is a state-of-the-art pretrained model designed for retrieval-based voice conversion training. It offers a robust solution for transforming voice characteristics from one speaker to another, providing high-quality results with minimal training effort.

Model Details

Titan-Medium

Training Environment: Utilized a RTX 3060 TI on Applio v3.1.1 (https://github.com/IAHispano/Applio), employing a batch size of 8 over a span of 3 weeks.
Iterations: X Steps
Epochs: X
Sampling rate: 40k
Fine-tuning Process: RVC 2 pretrained with pitch guidance, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725).

Titan-Large

Details forthcoming...

Collaborators

We appreciate the contributions of our collaborators who have helped in the development and refinement of TITAN.

Mustar
SimplCup

Beta Testers

We extend our gratitude to the beta testers who provided valuable feedback during the testing phase of TITAN.

SimplCup
Leo_Frixi

Citation

Should you find TITAN beneficial for your research endeavors or projects, we kindly request citing our repository:

@article{titan,
  title={TITAN: A Robust Pretrained Model for Retrieval-Based Voice Conversion Training},
  author={Blaise},
  journal={Hugging Face},
  year={2024},
  publisher={Blaise},
  url={https://huggingface.co/blaise-tk/TITAN/}
}