Inspiration
We wanted to be able to correctly read the mouths of individuals for those that are unable to hear for any reason.
What it does
Our program incorporates a neural network that guesses the phrase(s)/word(s) a person is saying.
How we built it
We used python, keras, and numpy along with a large dataset and created a font-end site using React and Tailwind CSS to display our process.
Challenges we ran into
A challenge we ran into was getting our validation loss and accuracy to work properly.
Accomplishments that we're proud of
We are proud that we were able to build a model as it was our first time ever attempting to do so.
What we learned
We learned how to build a model and filter out data how we intend.
What's next for Speech Reading Application
We're hoping to continue the project, making the program more usable and workable.
Log in or sign up for Devpost to join the conversation.