Deep Learning Engineer!
Toronto, Ontario
Joined April 2018
- Tweets3
- Following88
- Followers246
- Likes47
Speech to Speech models are about to get more impressive!
More at: block.xyz/dessa
Meet Dessa, our AI model trained from scratch on nothing but speech.
We believe speech is the natural interface for technology. So we built Dessa.
And we’re inviting AI safety researchers to explore Dessa.
Learn more: block.xyz/dessa
Rayhane Mama retweeted
(1/4) Last year, we introduced GSLM, the 1st language model that generates expressive speech using only raw audio recordings as input, breaking free dependence on text for training. Today, we’re sharing 3 research milestones: ai.facebook.com/blog/generat…
Happy to finally share our work!
Joint collaboration with Louay Hazami and Ragavan Thurairatnam.
Efficient-VDVAE obtain SOTA log-likelihood on 7 commonly used image datasets. We make an argument against 5-bit benchmarks and lay some ground work for downstream tasks with HVAEs.
Efficient-VDVAE: Less is more
abs: arxiv.org/abs/2203.13751
github: github.com/Rayhane-mamah/Eff…
simple modifications to the Very Deep VAE to make it
converge up to 2.6× faster, save up to 20× in memory load and improve stability during training
