NVIDIA Riva Speech Skills¶
NVIDIA Riva Speech Skills, version 1.5.0-beta is a toolkit for production-grade conversational AI inference.
The Riva Speech API server exposes a simple API for performing speech recognition, speech synthesis, and a variety of natural language processing inferences.
Pretrained models available from NGC.
Easy fine-tuning with Transfer Learning Toolkit.
Helm-managed cloud deployment.
Streaming and batch speech recognition.
Streaming and batch speech synthesis.
NLP models including question answering, entity recognition, and more.
- Quick Start Guide
- Release Notes
- Support Matrix
- Best Practices
- Speech Recognition
- Natural Language Processing
- Speech Synthesis
- Deploying Your Custom Model into Riva
- Local (Docker)
- NVIDIA Fleet Command
- gRPC & Protocol Buffers
- NGC Artifacts