Contents Menu Expand Light mode Dark mode Auto light/dark mode
TTS 0.10.2 documentation
Light Logo Dark Logo

Get started

  • Tutorial For Nervous Beginners
  • Installation
  • Humble FAQ
  • Contribution guidelines

Using 🐸TTS

  • Synthesizing Speech
  • Docker images
  • Basic inference
  • Start a server
  • Implementing a Model
  • Template 🐸TTS Model implementation
  • Training a Model
  • Multi-speaker Training
  • Fine-tuning a 🐸 TTS model
  • Configuration
  • Formatting Your Dataset
  • What makes a good TTS dataset
  • TTS Datasets

Main Classes

  • Trainer API
  • AudioProcessor API
  • Model API
  • Datasets
  • GAN API
  • Speaker Manager API

`tts` Models

  • Glow TTS
  • VITS
  • Forward TTS model(s)
  • 🌮 Tacotron 1 and 2
Back to top
Edit this page

TTS Datasets#

Some of the known public datasets that we successfully applied 🐸TTS:

  • English - LJ Speech

  • English - Nancy

  • English - TWEB

  • English - LibriTTS

  • English - VCTK

  • Multilingual - M-AI-Labs

  • Spanish - thx! @carlfm01

  • German - Thorsten OGVD

  • Japanese - Kokoro

  • Chinese

  • Ukrainian - LADA

Let us know if you use 🐸TTS on a different dataset.

Next
Trainer API
Previous
What makes a good TTS dataset
Copyright © 2021 Coqui GmbH, 2020 TTS authors
Made with Sphinx and @pradyunsg's Furo