/> speech-shield

Evaluate the quality and accuracy of text-to-speech generated audio. Regenerate when needed.

Using OpenAI's text-to-speech Whisper model and an implementation of the Levenshtein distance, speech-shield can evaluate the accuracy of text to speech snippets created.

Coming Q1 2024.

Join the CodeVideo Community.
© 2024 👨‍💻 with ❤️ by  Full Stack Craft
🎉 Proudly built as a part of the 2024 cohort of Backdrop Build