Starstruk Logo MarkStarstruk

v1.1

DigitalPhonetics/IMS-Toucanv1.1Feb 28, 2022by Flux9665

AI Summary

Introduces a new text frontend based on articulatory features and LAML-trained checkpoints for efficient speaker fine-tuning.

Key Highlights

  • Articulatory feature-based text frontend.
  • LAML (Model Agnostic Meta Learning) checkpoints.

New Features

  • Articulatory feature text frontend
  • LAML checkpoints

Full Release Notes

This release includes our new text frontend that uses articulatory features of phonemes instead of phoneme identities as well as checkpoints trained with a variant of model agnostic meta learning that are very well suited as basis for fine-tuning a single speaker model on very little data in lots of different languages.