Vision and conversational AI technologies are becoming ubiquitous, with countless applications taking advantage of object detection, image segmentation, action recognition, OCR, automatic speech recognition, natural language understanding, and speech synthesis coming to market. This webinar will present tools and technologies making the development of AI applications easier than ever.

We will start with an overview of the conversational AI landscape, and how you can build and deploy accelerated applications with state-of-the-art models using RIVA and NeMo. Then we will present DeepStream, a complete streaming analytics toolkit for AI-based multi-sensor processing, video, audio and image understanding. Finally, we will also introduce the TAO toolkit and pre-trained models giving you a faster, easier way to accelerate training and quickly create highly accurate and performant, domain-specific AI models.

• Get started with speech and vision AIs

• Key components for building real-time AI applications

• Train smarter with TAO Toolkit and finetuning

Content

content goes here