npc-engine 0.1.0

ZMQ JSONRPC 2.0 server for text generation and speech synthesis.

npc-engine

NPC-Engine is a deep learning inference engine for designing NPC AI with natural language.

Features

• Chat-bot dialogue system.

• SoTA tools like text semantic similarity and text to speech.

• Easy, open source deep learning model standard (ONNX with YAML configs).

• GPU accelerated inference with onnxruntime.

• Engine agnostic API through ZMQ server via JSONRPC 2.0.

Getting started

The easiest way to get started is to use NPC Engine through the Unity integration

You can also use it directly through ZMQ. See Documentation for more details.

Roadmap

Done:

• Real-time end-to-end chatbot dialogue system

• Semantic similarity

• Real-time speech to text (experimental)

• Unity integration

• CLI tool for importing models from Huggingface

• Asynchronous API features

In progress:

• Actions and planning

• Unreal integration

• Importing models from popular TTS libraries

• Emotion features

• Multiple languages support

• Much more

Build on Windows

• Create virtualenv and activate it:

  > python3 -m venv npc-engine-venv
  
  > .\npc-engine-venv\activate.bat
  

• Install dependencies

  
  > pip install -e .[dev,dml]
  
  

• (Optional) Compile, build and install your custom ONNX python runtime

  Build instructions here https://onnxruntime.ai/

• (Optional) Run tests

  • Download models to run tests against into npc-engine\resources\models.

  
  npc-engine download-default-models --models-path npc-engine\resources\models
  
  

  • Run tests with

  
  > tox
  
  

• Compile to exe with:

  
  > pyinstaller --additional-hooks-dir hooks --exclude-module matplotlib --exclude-module jupyter --exclude-module torch --exclude-module torchvision .\npc-engine\cli.py --onedir
  
  

Authors

• eublefar - Python, Neural Nets - github

• igorzmitrovich - Python, CI/CD - github

See also the list of contributors who participated in this project.