RJ Skerry-Ryan
@rjsr.bsky.social
🌮🤖 Speech and language modeling researcher.
Principal SWE @ Google Deepmind.
♊🌊 Gemini Audio and Astra core team.
http://rjryan.me/ https://google.github.io/tacotron
Principal SWE @ Google Deepmind.
♊🌊 Gemini Audio and Astra core team.
http://rjryan.me/ https://google.github.io/tacotron
I'm just wondering how you weaponize them (I assume) how small a payload they can carry, and mounting a gun on them would probably never work.
Sounds like dropping explosives is the easiest way to weaponize: kstatelibraries.pressbooks.pub/drone-delive...
Sounds like dropping explosives is the easiest way to weaponize: kstatelibraries.pressbooks.pub/drone-delive...
Explosives Delivered by Drone – DRONE DELIVERY OF CBNRECy – DEW WEAPONS Emerging Threats of Mini-Weapons of Mass Destruction and Disruption ( WMDD)Share on Twitter
kstatelibraries.pressbooks.pub
January 1, 2025 at 5:43 AM
I'm just wondering how you weaponize them (I assume) how small a payload they can carry, and mounting a gun on them would probably never work.
Sounds like dropping explosives is the easiest way to weaponize: kstatelibraries.pressbooks.pub/drone-delive...
Sounds like dropping explosives is the easiest way to weaponize: kstatelibraries.pressbooks.pub/drone-delive...
Nice! I'm surprised because the training window size is only 2.5 seconds, and the left context of the transformer is much longer than that, right?
December 3, 2024 at 6:07 AM
Nice! I'm surprised because the training window size is only 2.5 seconds, and the left context of the transformer is much longer than that, right?
Super cool! We did something similar for speech synthesis: arxiv.org/abs/2011.03568
Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis
We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the a...
arxiv.org
December 3, 2024 at 5:54 AM
Super cool! We did something similar for speech synthesis: arxiv.org/abs/2011.03568
Very nice! Does it generalize to arbitrary length inputs?
December 3, 2024 at 5:40 AM
Very nice! Does it generalize to arbitrary length inputs?
Don't forget text-to-speech!
November 28, 2024 at 9:49 PM
Don't forget text-to-speech!
Hm I think I was confused and thought the author of this dataset was banned:
huggingface.co/datasets/not...
That dataset is the instance of "You object to the use of your posts as data? I will make a dataset specifically of you."
huggingface.co/datasets/not...
That dataset is the instance of "You object to the use of your posts as data? I will make a dataset specifically of you."
noteuclaise/bluesky_1M_metaposts · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
November 28, 2024 at 8:42 PM
Hm I think I was confused and thought the author of this dataset was banned:
huggingface.co/datasets/not...
That dataset is the instance of "You object to the use of your posts as data? I will make a dataset specifically of you."
huggingface.co/datasets/not...
That dataset is the instance of "You object to the use of your posts as data? I will make a dataset specifically of you."
Maybe a bad analogy, IIUC a bunch of people said "I don't want you to do X.", some subset of those people were uncivil about it, and the response was to do X.
November 28, 2024 at 7:53 PM
Maybe a bad analogy, IIUC a bunch of people said "I don't want you to do X.", some subset of those people were uncivil about it, and the response was to do X.
Seems like bullying tbh.
I have to work hard to teach my kids that just because someone hits you doesn't mean you get to hit them back.
I have to work hard to teach my kids that just because someone hits you doesn't mean you get to hit them back.
November 28, 2024 at 5:35 PM
Seems like bullying tbh.
I have to work hard to teach my kids that just because someone hits you doesn't mean you get to hit them back.
I have to work hard to teach my kids that just because someone hits you doesn't mean you get to hit them back.
f-GAN is an absolute banger: arxiv.org/abs/1606.00709
The theory that developed around GANs is rich and (for me) was transformative.
The theory that developed around GANs is rich and (for me) was transformative.
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defi...
arxiv.org
November 28, 2024 at 5:37 AM
f-GAN is an absolute banger: arxiv.org/abs/1606.00709
The theory that developed around GANs is rich and (for me) was transformative.
The theory that developed around GANs is rich and (for me) was transformative.
