nielsinho
Re:SATO: Stable Text-to-Motion Framework
on Saturday May 04, 2024 @07:51AM (#40256952)
Unity is integrating a similar but more production-ready tool, Muse Animate, with their Muse platform. It does text-to-animation, and can fill in motion if you just provide keyframes. See usage here: https://youtu.be/tMCPz_yI7pY?si=OXAyxgGxHbCDywHm
Re:Visual Q-Learning Demo in JavaScript from Karpathy (2013)
on Sunday November 26, 2023 @02:54PM (#38424419)
I stumbled across ScriptBots when I was a kid, and became obsessed with implementing my own variants, and subsequently with neural networks. This one [1] is close to Karpathy's original, and this one [2] turns the world 3D and the beings are slightly more advanced. Both are implemented in MoonScript/Lua and run with Love2D. In part due to this this YouTube video, I work as a Machine Learning Engineer today.
[1] https://github.com/nilq/genesis [2] https://github.com/nilq/plane
Re:Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LLM, TTS, au...
on Saturday August 05, 2023 @05:31AM (#37010422)
TorToiSe is composed of many large models: GPT-2 for text encodings, as well as a large VQVAE encoder + large diffusion model decoder.
Only the big spaghetti inference code (+ weights) has been published, so there's a high entrance barrier for re-training / improving it.
Re:Show HN: Gdańsk AI – full stack AI voice chatbot (STT, LLM, TTS, au...
on Friday August 04, 2023 @05:05PM (#37005883)
TorToiSe (https://github.com/neonbjb/tortoise-tts) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.
Re:$Roku filed a Form 8-K revealing that $487M stuck at SVB (25% of cash)
on Saturday March 11, 2023 @03:06PM (#35112125)
Tissemand.
Re:Show HN: ML paper podcast generator using GPT and Tortoise-TTS
on Friday January 27, 2023 @02:50PM (#34550860)
It happens quite often with TorToiSe that it collapses in this way. Especially for unseen tokens that wouldn't have appeared in the training data, which likely consisted of a lot of transcribed stuff and read text like audio books. Trying to make it laugh by prompting it with "hahaha" (which you won't really see in mentioned data) often gets you demon and zombie noises.
Re:Show HN: ML paper podcast generator using GPT and Tortoise-TTS
on Friday January 27, 2023 @02:43PM (#34550765)
It uses the TorToiSe TTS model for generation. It's simple to generate conditioning voice latents using short audio samples. Likely transcribed JRE episodes were part of the TorToiSe training data, explaining how it's so good at recreating his voice characteristics in particular.
Re:Ask HN: What to do to be healthy when old?
on Monday October 03, 2022 @06:20AM (#33065551)
The book "Jellyfish Age Backwards" is very good and covers as well as sorts modern science in anti-aging and health. Definitely recommend this book.
Re:Tesla Dojo Custom AI Supercomputer at HC34
on Wednesday August 24, 2022 @04:00AM (#32576157)
You can take a look here: https://youtu.be/27PYlj-qNb0
Re:Who is going to replace Google for us?
on Monday June 27, 2022 @01:25PM (#31897760)
Are you sure it's Gmail sending you those advertisements?