Hacker News: petewarden

Speech Recognition and TTS in less than 500kb

petewarden — Tue, 14 Jul 2026 19:25:10 +0000

Article URL: https://github.com/moonshine-ai/moonshine/tree/main/micro

Comments URL: https://news.ycombinator.com/item?id=48911793

Points: 570

# Comments: 92

PiTorch: ML on Baremetal Raspberry Pis

petewarden — Wed, 08 Apr 2026 19:50:25 +0000

Article URL: https://masonjwang.com/projects/pitorch

Comments URL: https://news.ycombinator.com/item?id=47695386

Points: 1

# Comments: 0

Show HN: Moonshine Open-Weights STT models – higher accuracy than WhisperLargev3

petewarden — Tue, 24 Feb 2026 21:54:07 +0000

I wanted to share our new speech to text model, and the library to use them effectively. We're a small startup (six people, sub-$100k monthly GPU budget) so I'm proud of the work the team has done to create streaming STT models with lower word-error rates than OpenAI's largest Whisper model. Admittedly Large v3 is a couple of years old, but we're near the top the HF OpenASR leaderboard, even up against Nvidia's Parakeet family. Anyway, I'd love to get feedback on the models and software, and hear about what people might build with it.

Comments URL: https://news.ycombinator.com/item?id=47143755

Points: 316

# Comments: 81

New comment by petewarden in "Developer preview of TensorFlow Lite"

petewarden — Tue, 14 Nov 2017 23:40:13 +0000

One nice thing about Lite is that it's a lot easier to just include the operations you need (compared to TensorFlow 'classic'), there's fusion for common patterns, and the base interpreter is only 70KB. That covers a lot of the advantages of using XLA for mobile apps. In return you have the ability to load models separately from the code, and the ops are hand-optimized for ARM.

I'm still a fan of XLA, and I expect the two will grow closer over time, but I think Lite is better for a lot of scenarios on mobile.

New comment by petewarden in "Eager Execution: An imperative, define-by-run interface to TensorFlow"

petewarden — Tue, 31 Oct 2017 22:04:07 +0000

I'm the original author of the freeze_graph script, so I'm to blame for a lot of the on-going mess here. For what it's worth I'm actively working on cleaning this up, since I know what a painful experience it is. Apologies for everyone who's struggled with this, and I will take a look at the case number mentioned above and follow up internally to see if there's anything I can help with.

New comment by petewarden in "TensorFlow 1.0 Released"

petewarden — Wed, 15 Feb 2017 19:16:15 +0000

I'm not going to cover it in detail in my talk, but the code with some barebones documentation is available at https://github.com/tensorflow/tensorflow/tree/master/tensorf...

One thing to note is that this isn't available on production phones yet, because we need a signed driver to run within Android. You should be able to run this on a Dragonboard 820 development board though, using the instructions in the README.

This is all very new though, so apologies in advance for any hiccups getting up and running. My email's petewarden at google.com if you are trying this and hit problems.

New comment by petewarden in "Why GEMM is at the heart of deep learning"

petewarden — Tue, 21 Apr 2015 06:26:35 +0000

Yes, that was my screwup, sorry for any confusion! Despite multiple linear algebra courses, working in 3D graphics for a decade, I haven't internalized the basics of matrix notation. It doesn't help that my usual sandbox (Eigen) is column major by default, which is the wrong in-memory order for my raster-image trained brain to visualize. Funnily enough, I find tensor notation a bit easier, despite being less familiar.

Why is everyone so excited about deep learning?

petewarden — Tue, 10 Jun 2014 22:10:44 +0000

Article URL: http://petewarden.com/2014/06/10/why-is-everyone-so-excited-about-deep-learning/

Comments URL: https://news.ycombinator.com/item?id=7875613

Points: 1

# Comments: 0

Democratizing deep learning with an iPhone app and open source SDK

petewarden — Thu, 24 Apr 2014 22:17:31 +0000

Article URL: http://gigaom.com/2014/04/24/democratizing-deep-learning-with-an-iphone-app-and-open-source-sdk/

Comments URL: https://news.ycombinator.com/item?id=7643453

Points: 2

# Comments: 0

How to add a brain to your smart phone

petewarden — Tue, 08 Apr 2014 22:18:43 +0000

Article URL: http://petewarden.com/2014/04/08/how-to-add-a-brain-to-your-smart-phone/

Comments URL: https://news.ycombinator.com/item?id=7556383

Points: 17

# Comments: 2

Why deep belief matters

petewarden — Fri, 21 Mar 2014 00:35:56 +0000

Article URL: http://radar.oreilly.com/2014/03/why-deep-belief-matters-so-much.html

Comments URL: https://news.ycombinator.com/item?id=7439914

Points: 2

# Comments: 0

Deep belief image recognition running in JavaScript

petewarden — Wed, 19 Mar 2014 18:38:12 +0000

Article URL: https://www.jetpac.com/deepbelief

Comments URL: https://news.ycombinator.com/item?id=7430759

Points: 6

# Comments: 0

New comment by petewarden in "Ask HN: I'm a really lonely college student. What can I do?"

petewarden — Tue, 11 Feb 2014 02:27:18 +0000

I found college completely crushing, especially because I'd built up wild hopes for it as an escape from my unhappy childhood. I don't have any easy answers, but here's some of the tools that helped me:

- Exercise. I know, it sounds dumb, especially when you're depressed and have no energy, but it's an incredibly effective way of hacking your brain chemistry. Run, swim, bike, hike, just pick one and pour all your frustration, anger, and sadness into it.

- Get a hobby. I spent a lot of time worrying about being interesting to others, which guaranteed I wouldn't be. Being interesting is a many-body problem with lots of unknowns, but being interested is way more solvable. You can figure out what you like a lot more easily than you can guess what might make other people like you. Don't rule something out because it seems dorky, I guarantee you'll find other people who enjoy it too, even if it's Lego or collecting old maps. It's surprisingly hard to understand what you actually want though, especially if you've been focused on what other people think.

- Beware of magical transformations. I got married at 19, driven by an overwhelming desire to completely change my life to find happiness. It didn't work. I also took a lot of drugs. That didn't work either. I saw people get pulled into cult-like religions or extreme political groups. Drastic exterior changes don't alter who you are, you'll still have the same problems, no matter what anyone tells you. Focus on boring incremental improvements, like exercise and hobbies. I hated that idea, because I was in love with my life being dramatic and the basic stuff seemed so mundane, but it's what ended up making a lasting difference.

I doubt I'd have even listened to my present-day self when I was 19, but I hope there's something in there that helps you. Life really does get better.

How to analyze 100 million images for $624

petewarden — Tue, 10 Dec 2013 18:30:14 +0000

Article URL: http://radar.oreilly.com/2013/12/how-to-analyze-100-million-images-for-624.html

Comments URL: https://news.ycombinator.com/item?id=6882577

Points: 7

# Comments: 0

Dread Pirate Roberts' questions on StackOverflow

petewarden — Wed, 02 Oct 2013 17:48:05 +0000

Article URL: http://stackoverflow.com/users/1249338/frosty

Comments URL: https://news.ycombinator.com/item?id=6484012

Points: 4

# Comments: 0

Silk Road founder arrested

petewarden — Wed, 02 Oct 2013 15:28:43 +0000

Article URL: https://twitter.com/charlesarthur/status/385423843512561664

Comments URL: https://news.ycombinator.com/item?id=6482977

Points: 6

# Comments: 1

Why you should never trust a data scientist

petewarden — Thu, 18 Jul 2013 15:28:51 +0000

Article URL: http://petewarden.com/2013/07/18/why-you-should-never-trust-a-data-scientist/

Comments URL: https://news.ycombinator.com/item?id=6064251

Points: 8

# Comments: 0

No more heatmaps that are just population maps

petewarden — Mon, 20 May 2013 01:57:15 +0000

Article URL: http://petewarden.typepad.com/searchbrowser/2013/05/no-more-heatmaps-that-are-just-population-maps.html

Comments URL: https://news.ycombinator.com/item?id=5735395

Points: 5

# Comments: 0

New comment by petewarden in "How Solo Founders Beat The Odds and Get Into Top Accelerators"

petewarden — Wed, 13 Mar 2013 08:17:00 +0000

I went through Techstars in 2010 as their first solo founder, and I failed pretty hard. The combination of talks, mentor sessions, wooing potential team members, and pitch practice left me almost no time to code and plan the product. For the final pitch, all I had was demo ware, and I felt an idiot getting up on stage.

It was a worthwhile failure for me, I made some great friends and learned a lot, but I'd counsel any lone founder to focus on growing some kind of support team around them as the first priority. I would never contemplate an accelerator as a solo founder, but I have nothing but admiration for those who have managed it.

Stately - A US state map in a font

petewarden — Tue, 05 Feb 2013 19:12:31 +0000

Article URL: http://intridea.github.com/stately/

Comments URL: https://news.ycombinator.com/item?id=5172555

Points: 132

# Comments: 29