TechShark20 / mimcrycloner

A python notebook which uses two state of ther art models

 

About me ^{Linked in}      Video CLoning Notebook ^{TRY IT OUT}

 

Introduction

Want to stick an audio with a different persons video . have this link

1.A Video for face 2.A video for audio 3.A text and an audio

Text :: " i will run far away "
the output

result_voice.2.mp4

Getting Started

you need not do anything with the setup if you run it on google colab and a youtube video :

1. just copy paste the url for trimming
2. enter a url and trim it for text
3. add a text inside text synthesis
4. run the all code with gpu on colab

Resources

• Support diverse tasks

  The pretrained models were used , thank you to the authors for making this successful

1. *Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

   *Github

   *Used references(colab notebook)

2. *A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild

   *Github

   *Used references(colab notebook)