The following text is editable: Clear
Welcome to my innovative (Video to Speech & Text project), where cutting-edge technology meets the humble Raspberry Pi 3 Model B. Built using Angular 10 with Server-Side Rendering (SSR) and powered by Python and a tiny Language Model (LLM), this application offers an engaging and interactive experience for users.
The project features two primary functionalities:
The transcribed text is displayed dynamically, with a unique feature that highlights the text as it is played back through the embedded audio player. While the Raspberry Pi's performance may introduce some latency, the project showcases the potential of lightweight models in real-world applications.
This project not only demonstrates my ability to integrate various technologies but also highlights the possibilities of voice interaction on accessible hardware. I invite you to explore the functionalities and experience the blend of simplicity and innovation!