/portrait-synthesis-from-speech

This repository contains the main code for portrait synthesis from speech experiments associated with Retratista application. Refer to the application repository at https://github.com/DarkGeekMS/Retratista

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

Portrait Synthesis From Speech

This repository contains the main code for portrait synthesis from speech experiments associated with Retratista application.

Dependencies

  • Install python3 and python3-pip.

  • Install requirements.txt using PyPi :

    pip3 install -r requirements.txt

  • Alternatively, Dockerfile is provided with all required dependencies :

    # build image from dockerfile
docker build . -t portrait_syn_from_speech:latest
# run container from image in interactive session
docker run --runtime=nvidia -it portrait_syn_from_speech:latest /bin/bash

  • Refer to individual README.md inside each component folder for further installation notes.

System Architecture

Figure(1): Complete system architecture diagram showing the flow between different modules.

Refer to the wiki for more information about the project application, architecture and workflow.