Inspiration
We wanted to create a program that summarises lectures so that students can consume this content in a quick manner without the extra pauses and other meaningless words
What it does
This project takes in an mp4 video file as an input and outputs a summary in text form containing the key points mentioned in the video. The user can then copy the summarised text or save it for later reading.
How we built it
We used a Python Tkinter graphical interface to take in the input file through a navigation menu. We then separate the audio from the video file and pass the audio through an AI transcription model. This transcript passes through a GPT api to produce a summary of the transcript. The summary is displayed on the screen and the user can read, copy, or save it.
Challenges we ran into
None of our team members were competent with Tkinter or other graphical interface libraries in Python, so we had to learn its basics first which immediately set our team back. Furthermore, there were issues with the audio transcription section which we had to experiment with different installations of various modules.
Accomplishments that we're proud of
We managed to complete a successful working product which achieved our goal, we also learned lots on the way to creating this.
What we learned
Sleep is very important.
What's next for AI-Assisted Video Summariser
Integrate a text-to-speech option for the output, support different language outputs.
Built With
- chatgpt
- openai
- python
- visual-studio
Log in or sign up for Devpost to join the conversation.