Deepfakes & Voice Cloning: Machine Learning The Easy Way

Deepfakes & Voice Cloning: Machine Learning The Easy Way
Published 5/2023
MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz

Stable Diffusion, Midjourney, Generative AI, Fake News, +More for SEO, Internet Marketing, & Social Engineering!

What you’ll learn

Learn how to change lips / mouth movements for foreign film dubs

Voice cloning

TTS (text-to-speech)

Make anyone say whatever you want

Change what someone says in a video

Convert an image of a person into a moving video (motion copying)

Requirements

Be comfortable with using a computer and Google Colab

Description

Overview

Section 1: Introduction and Outline

Lecture 1 Introduction

Lecture 2 Project Scope

Lecture 3 Outline and Workflow

Lecture 4 Course Resources

Section 2: Voice Cloning

Lecture 5 Tortoise-TTS

Lecture 6 Installing Tortoise-TTS

Lecture 7 Descript

Section 3: Video DeepFakes

Lecture 8 Wav2Lip

Lecture 9 Synthesia

Lecture 10 Thin-Plate Spline Motion Model (pt 1)

Lecture 11 Thin-Plate Spline Motion Model (pt 2)

Lecture 12 Useful FFmpeg Commands

Section 4: Environment Setup Guidelines

Lecture 13 Pre-Installation Check

Lecture 14 Environment Setup: Install Python With Anaconda

Lecture 15 Environment Setup: Install Python Without Anaconda (not recommended)

Lecture 16 Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer