Jarvis 1.0 Beta: What’s New
Jarvis 1.0 Beta includes fully optimized pipelines for deploying real-time conversational AI apps such as transcription, virtual assistants and chatbots.
- ASR, NLU, and TTS models in NGC trained on thousands of hours of speech data
- Integration with Transfer Learning Toolkit to re-train on custom data for ASR and NLU apps
- 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
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 Jarvis 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 Jarvis Speech Services.
Additional Jarvis Resources
Fine-Tuning with TLT
You can quickly start with NVIDIA’s free pre-trained models and fine tune them using Transfer Learning Toolkit in Jarvis. NGC contains the following models & example notebooks for speech recognition and natural language understanding.
Download TLT pre-trained models from NGC.
- Speech Recognition
- Question Answering
- Text Classification
- Named Entity Recognition
- Punctuation & Capitalization
- Intent Detection & Slot Tagging
Building Real-Time Apps with Jarvis 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.