Inspiration

Interested in working with machine learning and the Clarifai API.

What it does

Can take audio and convert it into a picture to have it analyzed by Clarifai's machine learning.

How we built it

We used a space filled curve library to create visual representations of audio binaries. We trained a model to recognize words from pictures.

Challenges we ran into

Some challenges we ran into were finding a way to represent the audio binaries as a picture. Our original approach was through javascript but later reverted to python in order to work with the space filled curve library.

Accomplishments that we're proud of

We successfully communicated with an API. It was our first time working with machine learning and we were excited to see our model respond so positively.

What we learned

We learned how to train a Clarifai model and what a space filled curve was. We also learned how to manage a project with git.

What's next for ADKI

A GUI to help with training and streamline the experience. More words for our model to recognize.

Built With

Share this project:
×

Updates