Inspiration
Our inspiration was watching videos and being unable to find something we had seen before.
What it does
It parses the audio file and gets time stamps on things said, which are then processed by us to reveal the first occurrence of any string in the file's time in the audio file in seconds.
How we built it
We built it with google cloud platform speech to text api, python flask backend, react front end, and used docker to connect all the end points.
Challenges we ran into
We ran into massive problems with trying to get docker compose running all the containers as well as with our python code working and finally with our front end having trouble connecting to backend.
Accomplishments that we're proud of
We learned a lot and managed to get our backend to work and we got something really presentable which has an application.
What we learned
We learned a bit about google cloud platform and docker, and full stack developement.
What's next for PhraseFindr
Next would be nailing down the front end to make it even more of a presentable project.
Log in or sign up for Devpost to join the conversation.