NVIDIA Jarvis Speech Skills
1.0.0-c38e53b
Version select:
  • Documentation home

User Guide

  • Quick Start Guide
    • Overview
    • Prerequisites
    • Models Available For Deployment
      • Automatic Speech Recognition
      • Natural Language Processing
      • Text-to-Speech
    • Local Deployment Using Quick Start Scripts
      • Configuring
      • Downloading Required Models and Containers From NGC
      • Launching the Servers and Client Container
      • Stopping
      • Removing
    • Using Helm To Deploy Jarvis AI Services on Kubernetes
      • Kubernetes Secrets
      • Jarvis Settings
    • Running The Jarvis Client And Transcribing Audio Files
    • Running The Jarvis Client And Converting Text To Audio Files
    • Integrating Jarvis AI Services Into Your Own Application
      • Python Example
    • Support
  • Automatic Speech Recognition
    • Introduction
      • Benefits Of Jarvis ASR
    • Jasper
      • Modules
    • Training A Model With Your Data
    • Generating The Triton Inference Server Model Repository
      • Creating A Model Repository Using A Pre-Trained NGC Model
      • Creating A Model Repository Using A Fine-Tuned Model From NeMo
      • Modifying The Model Repository To Use Custom Language Model
    • Deploying Your Model
      • Deploying A Model Using A Docker Container
      • Deploying A Model Using A Helm Chart
    • Using The Jarvis ASR Service
      • Interacting With The Jarvis ASR Service Using Pre-Generated Python Bindings
      • Interacting With The Jarvis ASR Service Using The Provided C++ Clients
    • Troubleshooting And Support
      • FAQs
  • Natural Language Processing
    • Introduction
      • Benefits Of Jarvis NLP
      • API
    • BERT
      • Modules
    • Training A Model With Your Data
      • BERT
      • Named Entity Recognition
      • Intent Detection and Slot Tagging
      • Domain Classification
      • Punctuation
    • Generating The Triton Inference Server Model Repository
      • Pretrained NLP Models On NGC
      • Creating A Model Repository Using A Fine-Tuned Model From NeMo
    • Deploying Your Model
      • Deploying A Model Using A Docker Container
      • Deploying A Model Using A Helm Chart
    • Using The Jarvis NLP Service
      • Interacting With The Jarvis NLP Service Using The gRPC API
      • Interacting With The Jarvis NLP Service Using The Python API
    • Integrating NLP With Jarvis
    • Troubleshooting And Support
  • Text-to-Speech
    • Introduction
      • Benefits Of Jarvis TTS
    • Tacotron 2 + Waveglow
      • Modules
    • Training A Model With Your Data
    • Exporting The Checkpoints From NeMo To Jarvis
    • Generating The Triton Inference Server Model Repository
      • Creating A Model Repository Using A Pre-Trained NGC Model
      • Creating A Model Repository Using A Fine-Tuned Model From NeMo
    • Deploying Your Model
      • Deploying A Model Using A Docker Container
      • Deploying A Model Using A Helm Chart
    • Using The Jarvis TTS Service
      • Interacting With The Jarvis TTS Service Using The gRPC API
      • Interacting With The Jarvis TTS Service Using The Python API
    • Integrating TTS With Jarvis
    • Troubleshooting And Support

Reference

  • gRPC API
    • src/jarvis_proto/jarvis_asr.proto
    • src/jarvis_proto/jarvis_nlp.proto
    • src/jarvis_proto/jarvis_nlp_core.proto
    • src/jarvis_proto/jarvis_tts.proto
    • src/jarvis_proto/audio.proto
    • src/jarvis_proto/health.proto
  • C++ API
    • Class Hierarchy
    • File Hierarchy
    • Full API
      • Classes and Structs
        • Class HealthImpl
NVIDIA Jarvis Speech Skills
  • Docs »
  • <no title>
  • View page source

© Copyright 2018-2020, NVIDIA Corporation

Built with Sphinx using a theme provided by Read the Docs.