Inspiration
Juggling the DeltaHacks hackathon with college course loads made us realise how little free time the average STEM student has in their schedule. We resolved to solve this with an application that would make revisions and pre-class watches easier.
What it does
The application takes a file or link from the user containing a video file, and converts it into an easy-to-read text summary.
How we built it
We built a Python script that used the AssemblyAI speech-to-text API to convert a lecture recording into a full transcript. Then, we passed this transcript to the Sassbook AI text summarization API to create a deep-learning based summary of the text. This is then fed back through our Flutter frontend and displayed to the user.
Challenges we ran into
The primary challenge was linking Python and Flutter to add a proper frontend and backend. Although we thought there would be many projects like this, but unfortunately we could not find many resources online.
Accomplishments that we're proud of
For most of us, this was our first designed app that used both a detailed frontend and a backend. We are also proud of the idea we came up with and how (relatively) simple the execution logic was.
What we learned
We learned more about Flutter and Python, as well as the utility of AssemblyAI APIs and how to effectively design a UI that adhered to the theme of our application.
What's next for Brevity
We hope to include many more features, such as user logins and a central server that can catalog video summaries once they are done. This would save processing time for future requests. In addition, we hope to make professor-specific trained neural networks to create more accurate transcripts and summaries.
Log in or sign up for Devpost to join the conversation.