“True conversational AI is a voice assistant that can engage in human-like dialogue, capturing context and providing intelligent responses. Such AI models must be massive and highly complex,” Sid Sharma from ‘What Is Conversational AI?’. This lecture attempts to demystify conversational AI by covering its counterparts that include, but not limited to: Automatic Speech Recognition, Natural Language Processing & Understanding, Text-to-Speech Synthesis, Intention Extraction and Identification, etc… We use NVIDIA’s Jarvis, an application framework for multimodal conversational AI services that delivers real-time performance on GPUs, to perform sophisticated conversational AI tasks. By the end of the lecture, we present a Question/Answering Demo powered by NVIDIA’s Jarvis. This lecture is outlined as follows:


  • 00:00 Highlights
  • 00:30 Introduction
  • 01:18 What is Jarvis ?
  • 03:44 System Requirements
  • 04:24 Docker Installation
  • 05:52 CUDA Installation
  • 06:59 NGC Setup
  • 09:15 Jarvis Setup
  • 11:22 Jupyter Notebook Setup
  • 11:51 Connecting to Jarvis Servers
  • 18:02 ASR: Automatic Speech Recognition
  • 28:39 Core NLP: Punctuation Model
  • 33:43 Core NLP: Token Classification API
  • 36:00 Core NLP: Text Classification
  • 39:35 TTS: Text-to-Speech Synthesis
  • 43:14 NLP: Intention Analysis
  • 45:50 Synchronous Requests
  • 47:48 Asynchronous Requests
  • 48:53 Question/Answering Jarvis App
  • 54:39 Summary

GTC Conference: https://www.nvidia.com/en-us/gtc/?ncid=ref-crea-882872
Jarvis is @ https://nvda.ws/3afJXJW

Subscribe: https://www.youtube.com/@AhmadBazzi/featured 

#python #ai #artificial-intelligence #developer

NVIDIA Jarvis Conversational AI on Python
1.00K GEEK