Riva 1.0 Beta: What’s New
Riva 1.0 Beta includes fully optimized pipelines for deploying real-time conversational AI applications such as transcription, virtual assistants and chatbots.
- Automatic speech recognition (ASR), natural language understanding (NLU), and text-to-speech (TTS) models in the NVIDIA NGC™ catalog trained on thousands of hours of speech data
- Integration with the NVIDIA TAO Toolkit to re-train on custom data
- Fully accelerated deep learning pipelines optimized to run as scalable services
- End-to-end workflow and tools to deploy services using one line of code
Riva Studio is Available in Early Access
Riva Studio is an Integrated Development Environment (IDE) for authoring, training, and deploying multimodal virtual assistants.Apply for Early Access
Quick Start Guide
Step-by-step guide to deploy pretrained models as services on a local workstation and interact with them through a client.
Learn about the architecture, key features and components in Riva that help you build multimodal conversational AI services.
Sample demonstrating a simple but complete real-time, domain-specific conversational AI app.
Virtual Assistant (with Rasa)
App showing how to integrate the Rasa Dialog Manager with Riva speech services.
Additional Riva Resources
Fine-Tuning with TAO Toolkit
You can quickly start with NVIDIA’s free pre-trained models and fine-tune them using the TAO Toolkit in Riva. NGC contains the following models and example notebooks for speech recognition and natural language understanding.
Download TAO Toolkit pre-trained models from NGC.
- Speech Recognition
- Question Answering
- Text Classification
- Named Entity Recognition
- Punctuation and Capitalization
- Intent Detection and Slot Tagging
Build Real-Time Apps with Riva Services
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.