NVIDIA Jarvis Conversational AI on Python


“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.

The lecture above shows you how to install Jarvis on your machine. This is done by first installing Docker, then CUDA, registering to NGC, then finally setting up Jarvis. You can work with Jarvis on a Jupyter notebook.

Ahmad Bazzi then shows you how to work with the most essential components of Jarvis that are: ASR (Automatic Speech Recognition)
NLP (Natural Language Processing) and Core NLP, and finally TTS (Text-to-Speech) Synthesis.

A very cool Question/Answering Jarvis-based demo is finally presented in the tutorial. It is trained via Wikipedia articles making use of the wikipedia python package.

Ahmad Bazzi

Ahmad Bazzi is an Electrical Engineer and YouTuber. Ahmad Bazzi is a signal processing engineer at CEVA DSP. He holds a PhD in Electrical Engineering from EURECOM. Ahmad Bazzi is a EURECOM alumni. Ahmad Bazzi obtained his Master studies (Summa Cum Laude) in Electrical Engineering at SUPELEC, Paris. Ahmad Bazzi has many publications in well-known IEEE conferences, including a nomination award and is a co-inventor in several patents. Ahmad Bazzi dedicates time to publish high level lectures on Mathematics (including convex optimization) and Programming. Ahmad Bazzi also focuses on Machine Learning, Convex Optimization, Linear Algebra, Python, SymPy, NumPy, Pandas, CVXOPT, MATLAB, C++ for firmware systems.

One thought on “NVIDIA Jarvis Conversational AI on Python

Leave a Reply

Your email address will not be published. Required fields are marked *

Next Post

Selenium Automation on Python

Sat Mar 13 , 2021
The Selenium Python package is automates web driver interaction via Python. Selenium provides a simple API to write functional tests using WebDriver. Selenium Python bindings provide a convenient API to access Selenium WebDrivers like Chrome, Safari, Firefox, Opera, Edge, Blackberry, and many more. This lecture aims at covering all related […]

You May Like