DLRG Mini-Course: Building Transformers Models for Conversational AI tools 2

Title: Building Transformers Models for Conversational AI Tools
Date: Nov 13, 2023
Time: 1-3:30 pm CST
Location: Online

https://forms.gle/o8t4NAnEcfBE1GJ6A

Learning Objectives

Learn how to quickly build and deploy production-quality speech AI applications with real-time transcription and natural language processing (NLP) capabilities.
speech AI pipelines are complex and expensive to develop from scratch. In this course, you’ll learn to build a speech AI service using the NVIDIA Riva framework. Riva provides a complete, GPU-accelerated software stack, making it easy for developers to quickly create, deploy, and run end-to-end, real-time speech AI applications that can understand terminology unique to each company and its customers. The Riva framework includes pretrained speech AI models, tools, and optimized services for speech, vision, and natural language understanding (NLU) tasks. With Riva, developers can create customized language-based AI services for intelligent virtual assistants, virtual customer service agents, real-time transcription, multi-user diarization, chatbots and much more.
In this course, you will integrate NVIDIA Riva automatic speech recognition (ASR) and named entity recognition (NER) models with a web-based application to produce transcriptions of audio inputs with highlighted relevant text. You’ll then customize the NER model using NVIDIA TAO Toolkit to provide different targeted highlights for the application. Finally, you’ll explore production-level deployment performance and scaling considerations of Riva services with Helm Charts and Kubernetes clusters.

 

You’ll learn how to:

 

• Deploy and enable pretrained ASR and NER models on Riva for a speech AI Application
• Explore the Riva ASR service with audio examples
• Fine-tune and deploy a domain-specific NER model with TAO Toolkit
• Deploy a production-level speech AI application with a Helm Chart for scaling in Kubernetes clusters

 

Upon completion, you’ll be able to build speech AI applications and deploy them as services.

 

Course Details

 

Prerequisites: Python programming experience, basic understanding of neural networks, and a fundamental understanding of a deep learning framework such as TensorFlow or PyTorch

In addition, this lab requires that the user have an NVIDIA GPU Cloud (NGC) account and API key. If you have not done so already, please:

1. Register and activate a free NGC account
2. Generate your NGC API key and save it in a safe location

 

Tools, libraries, frameworks used: Riva, TAO Toolkit, Kubernetes