Ask HN: How can I clone myself using ML?
What beginner-friendly tools and models can I use to create a backup of my voice (text 2 speech and the like), appearance (video in real time) etc? > beginner-friendly > video in real time These two are going to be mutually exclusive for a few years, I'm afraid. Sure, the hardware investment will put you back a few thousand dollars, but running the latest temporally-stable video models is not realistic for most experienced devs, much less a beginner. If you wanted to be corny you could train a few-shot voice model to sound like you and plug it into GPT-3, but that would be neither realtime nor particularly gratifying. It's not exactly a surprise that this is a bad idea. Now I'm going to get nightmares with my AI doppelganger repeating GPT-3 gobbledygook in monotone... I am a software engineer but yeah definitely a beginner when it comes to ML. RE: resources/hardware. I'd rather go for cloud providers like Microsoft's Azure Cognitive services or some pre-trained model that I can run locally or on colab by Google. I would like some guidance on which models to choose, tutorials and/or perhaps colab links with examples on how to use them. I like the idea to leave a trained model with my voice to my loved ones at least for when I will be gone. I would love to have one of my dad too! Start logging and recording yourself constantly build up a database essentially of you. Have videos of you doing motions. Videos of you walking in different directions. Have recordings of your speech and singing. Just have everything of you as much as you can because that'll be probably what you need if you want to just make a clone of the physical representation of you. I like the cut of your jib. This makes me realize I can follow the same steps, then threaten to clone myself and make beaucoup bucks on the ransom. I’m sure plenty of people would pay to stop that from happening.