Starstruk Logo MarkStarstruk

v2.3

DigitalPhonetics/IMS-Toucanv2.3Oct 25, 2022by Flux9665

AI Summary

Adds controllable speaker features through self-contained embeddings and replaces the vocoder with Avocodo for better performance.

Key Highlights

  • Self-contained embeddings for TTS conditioning.
  • Avocodo vocoder replaces HiFi-GAN.
  • New artificial speaker generation options.
  • Weights & Biases integration.
  • Automated model downloading.

Breaking Changes

  • Backwards compatibility is broken.

New Features

  • Self-contained embeddings
  • Avocodo vocoder
  • Artificial speaker generation
  • Weights & Biases integration
  • Automated model downloading

Full Release Notes

This release extends the toolkits functionality and provides new checkpoints.

- self contained embeddings: we no longer use an external embedding model for TTS conditioning. Instead we train one that is specifically tailored for this use.
- new vocoder: Avocodo replaces HiFi-GAN
- new controllability options through artificial speaker generation
- quality of life changes, such as weights&biases integration, a graphic demo script and automated model downloading
- divese bugfixes and speed increases

This release breaks backwards compatibility, please download the new models or stick to a prior release if you rely on your old models.