Inspiration
With the number of articles and video tutorials for anything increasing everyday, we wondered which one is the best. None of us particularly enjoy listening to long, boring lectures that drag on for two hours too long. That being said, we also don't like reading pages and pages of text. This is where our tool comes in, and how it can glorify anyone's sluggish habits.
What it does
TL;DL takes an audio input and converts it into a concise summary, complete with a list of key words.
How we built it
We built it using Python, utilizing the speechrecognition package along with the Google API speech recognition tool for speech recognition, the pyaudio package for reading data from a microphone input and PyQt5 for a graphical user interface.
Challenges we ran into
A lot of the programming for this project was less writing and more reading and understanding new packages previously unfamiliar to us. We found this type of programming very different and struggled the most with this (especially with PyQt5).
Accomplishments that we're proud of
We successfully implemented exactly what we wanted to. It might not be overly optimized, but it works in a general purpose kind of way.
What we learned
None of the packages we used were familiar to us. Almost everything we wrote was completely new territory and we used each tool the most effectively possible with our limited knowledge. It was my (Ali) first experimentation with GUIs in Python.
What's next for TL;DL
This tool can be heavily optimized. File managing can be done better and the GUI can use some refinements.
Log in or sign up for Devpost to join the conversation.