#TITAN: A Versatile, Robust, and High-Quality Pretrained Model

1 messages · Page 1 of 1 (latest)

runic zephyr
#

TITAN is a state-of-the-art pretrained model designed for RVC 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

Collaborators

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

  • Mustar
  • SimplCup
  • UnitedShoes

Beta Testers

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

  • SimplCup
  • Leo_Frixi
  • Light
  • SCRFilms
  • Ryanz
  • Litsa_the_dancer

Download

TITAN is currently the best general-purpose pretrained for RVC. I strongly recommend future pretrained creators to start their finetuning from TITAN!

#

Feel free to attach samples you have created with TITAN. On the official HuggingFace website you can find some comparisons with other models.

If you have any questions regarding TITAN, please use the respective channels (#✨│ai-help / #🔊│ai-development) and feel free to mention me. Avoid writing here as it may cause doubts to new users.

vivid sorrel
mortal sand
vivid sorrel
#

seen speaker dataset, quality and artifacting test.
1min and 52s dataset, mangio crepe 8 hops, batch 2, titan pretrain

vivid sorrel
dire lagoon
#

The TITAN pretrain did pretty good with only 7 seconds of data of Adam from elevenlabs at 200 epochs

mighty flume