The problem ATRIS - Auto Transcribe Intelligent and Smart solves
Problem our company observes and wants to solve:
Google Speech To Text
-
Text gets cluttered and there is no feature to describe who spoke the statement.
Smart Enough
-
Existing solutions don't effectively handle the data post transcribe.
Full Of Integration
-
It's difficult to sync task between the transcribe platform to todos and notes.
Differentiate Multiple Speakers
-
Difficult to get content of particular speaker, as text is cluttered.
Challenges we ran into
We observed few challenges as below:
-
Training the Machine Learning Datasets
-
Implementing the complex UI
-
Creating BackEnd APIs
-
Real-Time WebSocket communication between FrontEnd and BackEnd
-
Showing Real-Time datas
-
Processing with Machine Learning models