AI Transcription Challenges
Mike and Chris discuss the challenges of transcription accuracy and the use of multiple models to handle variability in accents and dialects. They explore the idea of using different models for different call types and tease a new product in development at Invoca.In this clip
From this podcast
Practical AI
Real-time conversational insights from phone call data
Related Questions
Is any large language model (LLM) being used to train transcripts?
Are you using multiple models in your workflow as you're coming through this, or is there one master model? Which approach are you taking, and how do you account for variability within the different speakers?
So do you have different models that analyze the different parts of the call, or are you kind of just saying we have one big model that has enough complexity to handle all those things?