Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/hcmlab/melax

https://github.com/hcmlab/melax

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.7%) to scientific vocabulary
Last synced: 6 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: hcmlab
  • License: bsd-3-clause
  • Language: Python
  • Default Branch: main
  • Size: 13.1 MB
Statistics
  • Stars: 1
  • Watchers: 4
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Created over 1 year ago · Last pushed 10 months ago
Metadata Files
Readme License

README.md

🚀 Omniverse & Melax Setup Guide

🎮 Omniverse Installation & Configuration

  1. Download Omniverse Launcher

  2. Create & Log in to NVIDIA Account

    • Sign up or log in as required.

  3. Set Path Configuration txt Library Path: C:\Users\YourName\AppData\Local\ov\pkg DATA Path: C:\Users\YourName\AppData\Local\ov\data Content Path: C:\Users\YourName\Downloads CACHE Path: C:\Users\YourName\AppData\Local\ov\cache

  4. Launch Omniverse

  5. Install Audio2Face

    • Navigate to Exchange → Search for Audio2Face
    • Download version 2023.1.1

  6. Run Audio2Face in Headless Mode

    • Edit start_headless.bat with the correct path: bat set TARGET_BATCH="C:\Users\YourName\AppData\Local\ov\pkg\audio2face-2023.1.1\audio2face_headless.bat"

🧠 Melax Setup

  1. clone from https://github.com/hcmlab/melax.git

  2. Run Installer Download Cora

    • Download the character developed in Unreal Engine 5.3: https://uniaugsburg-my.sharepoint.com/:f:/g/personal/daksithawithanagedonuni-ade/EnzWciX1_OJHkfvTXJhz4Z0BQl1aWLAdLkRg-tJZsKZ04w?e=PE9Ao0 The GUI and Audio2Face server must be running.

    - Execute MeLaX_ACE_A2F_Only.exe

  3. Network Permissions

    • On first run, allow access on Public, Private, and Domain networks.

  4. Download Ollama

    • Ensure it is installed on your system. https://ollama.com/download/windows

🐍 Running mainwindow.py

  1. Install Python Packages

    • From requirements_python3_11.txt (for Python 3.11)

  2. Install ffmpeg if not already installed

  3. Run the GUI bash python gui.py

Once everything is running: In the GUI load the a2f model: select 'female.usd' and press load button. Select your microphone and choices of AST, LLM, TTS. The press play button on the GUI.

You should be able to speak to the character in an interactive manner.

Owner

  • Name: Human Centered Artifical Intelligence
  • Login: hcmlab
  • Kind: organization
  • Location: Augsburg, Germany

Human Centered Artifical Intelligence Lab of the Augsburg University

GitHub Events

Total
  • Watch event: 1
  • Public event: 1
  • Push event: 10
Last Year
  • Watch event: 1
  • Public event: 1
  • Push event: 10