Skip to content

Latest commit

 

History

History
3 lines (3 loc) · 349 Bytes

README.md

File metadata and controls

3 lines (3 loc) · 349 Bytes

Text-Summarization-From-Speech

This model performs automation speech recognition to convert audio signals to text and then the text is further fed to a transformer that summarizes the text. This is an end to end pipeline that involves ingestion of data including text and audio, validation, transformation ,training, evaluation and deployement