Beginner-friendly documentation for preparing speech datasets, training and fine-tuning text-to-speech models, running inference, packaging models, and troubleshooting common problems.
- Read the published guide
- Start with the documentation source
- Guide 1: Data Preparation
- Guide 2: Training Setup
- Guide 3: Model Training
- Guide 4: Inference
- Guide 5: Packaging and Sharing
- Guide 6: Troubleshooting and Resources
- Glossary
- Translation guide
- Licence
The site is available in English, Bulgarian, Spanish, French, and Italian. Each language follows the same guide structure so translations can be compared and maintained consistently.
docs/contains the MkDocs source tree.docs/bg/,docs/es/,docs/fr/, anddocs/it/contain localized pages.mkdocs.ymlconfigures the documentation site, navigation, languages, and themes..github/workflows/mkdocs-gh-pages.ymlbuilds and deploys the site to GitHub Pages.site/is generated output and is intentionally ignored by Git.
Corrections, clearer explanations, new examples, and translation improvements are welcome. Please keep the shared structure intact, leave executable commands and code identifiers in English, and follow the translation guide when adding or updating a language.
The guide is released under the Creative Commons Attribution 4.0 International License. See LICENCE.md for the full notice.