Our speech-to-text model is primarily based off of Nvidia's NeMo CitriNet, however, it has been modified and improved to meet our use case.
What ML model/algorithms/techniques do you use?
Updated this week
Did this answer your question?
Copyright (c) 2023, Intercom, Inc. ([email protected]) with Reserved Font Name "Lato".
This Font Software is licensed under the SIL Open Font License, Version 1.1.Skip to main content