James Betker

[James Betker @neonbjb]

A few interesting ways to understand how diffusion models work: https://t.co/999w9bmpyW

[James Betker @neonbjb]

I just posted a write-up on my deep-learning hardware: https://t.co/HvUrEe6erV

[James Betker @neonbjb]

I released TorToiSe v2.3 tonight. The main new feature is a new CLVP model. 6x more parameters, 20% better performance on the validation set. TorToiSe itself performs ~5% better by https://t.co/nnmwJk3l3v

[James Betker @neonbjb]

Friends don't let friends train small diffusion models: https://t.co/ndQQZlnP4X

[James Betker @neonbjb]

Tortoise v2 is out! https://t.co/Z8QPVMdaOu

[James Betker @neonbjb]

https://t.co/Z8QPVMdaOu a DALL-E like text-to-speech model trained on 16M speech samples.

[James Betker @neonbjb]

I'd like to share ocotillo - an extremely simple speech to text library that uses wav2vec. Github: https://t.co/HXgY9iprOA Blog post: https://t.co/9YW0epOevV