Skip to content

Latest commit

 

History

History
3 lines (2 loc) · 407 Bytes

README.md

File metadata and controls

3 lines (2 loc) · 407 Bytes

Text to Speech: The Cardinal way

The Cardinal Development team is developing an AI-powered voice generation system that converts text into natural-sounding speech currently for both English and Arabic. This project combines deep learning techniques, such as sequence-to-sequence models and attention mechanisms, with a diverse and aligned dataset of high-quality audio recordings and corresponding text.