Building Conversational AI Applications

8 hours of instruction

Discover how to quickly build and deploy production quality conversational AI applications with real-time transcription and natural language processing capabilities.

OBJECTIVES

1. How to deploy and enable pretrained ASR and NER models on Riva for a conversational AI application
2. How to fine-tune and deploy domain-specific models with TAO Toolkit
3. How to deploy a production-level conversational AI application with a Helm Chart for scaling in Kubernetes clusters

PREREQUISITES

None

SYLLABUS & TOPICS COVERED

1. Introduction
   • Meet the instructor
   • Create an account
2. Introduction To Conversational AI
   • Work through a TAO Toolkit model inference example with speech recognition
   • Deploy Riva ASR and NER models
   • Launch a contact application with ASR and NER
3. Model Customization
   • Fine-tune NER for a specific domain
   • Deploy a customized NER model within Riva
   • Launch the application with updated models
4. Final Review
   • Review key learnings and answer questions.
   • Complete the assessment and earn a certificate.
   • Complete the workshop survey.
   • Learn how to set up your own AI application development environment

SOFTWARE REQUIREMENTS

Each participant will be provided with dedicated access to a fully configured, GPU-accelerated workstation in the cloud.