README.md

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 pretrained with pitch guidance, leveraging an 11.15-hour dataset sourced from Expresso (https://arxiv.org/abs/2308.05725).

Titan-Large

• Details forthcoming...

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/}
}