deivid

Same, I got a Withings watch, which is both

Nice! I also got tired of the Withings app (which now pushes AI subscriptions, wtf) and "made" an app for the smartwatches (at least, it works with my ScanWatch 2)

The app is at https://github.com/DavidVentura/withouthings - the firmware on the watch was leaked as well, and it's been helpful to debug some of the protocol.

Kokoro can be hacked a bit (see script https://github.com/DavidVentura/translator-rs/blob/master/sc... ) which makes it about 3x faster.

My phone went from slightly slower than realtime to very comfortable (also lower latency on first utterance!)

PaddlePaddle (v6) is fantastic and fast

Love the idea, but I can't handle the big screens on these smart watches. To me it feels like having a fisher price toy on my wrist. Hopefully a more open alternative to Withings will emerge

Depending on what data you want, you can try Withings watches. I'm currently reversing the protocol and it mostly works.

For me, sloppy content is worse than no content. I'd rather have 3 sentences written by a human than a wall of Claudespeak.

Do you have an RSS or a way to subscribe to the TTS work you are doing? Your newsletter button is just a mailto link

It's supposed to handle acceleration though, if you bring your phone to your face quickly dots get larger. I've done some in-car testing, but things get squeamish quickly so it's not the easiest to validate.

Changing the color / adding some contrast would be quite a simple change

Interesting project, but the slop readme made me quit reading halfway

send me an email

send me an email

I spent a day fiddling with AI and dropping the expensive layers in kokoro, on phones, on CPU, on MNN, it runs 3x faster.

Quality is very close.

Will vary in your setup, but here is my script: https://github.com/DavidVentura/translator-rs/blob/master/sc...

I am making (open) finetunes for malayalam and kannada (and bengali, gujarati, hebrew), and need someone to transcribe a few images for me. Could you contact me if you are interested in helping?

Amazing! I'd recommend using PaddlePaddle OCR models if you want to make your handwriting conversion local, it's definitely fast enough. Probably faster than the Sonnet call.

I tried the model on your handwriting and it worked great. My handwriting is bad enough that it doesn't work :)

Commercial or FOSS? I've been researching the mobile side and it's very exciting!

Sounds great, but if you din't cave to apple/google (eg: graphene, lineage), models are not built-in. Every app needs to ship their own models, and they are not tiny.

Is there a solution for this? I'm currently just making users download onnx models if they want a feature, but it's not smooth UX

There's definitely a much smaller, cleaner kubernetes hiding inside the current monstrosity.

LB, Services, pods, DNS gets you like 99% of the way there

How do you manage to finish things? After a while, for me, the novelty high wears out, and instead it becomes a wall. Some project require something silly, like sending 1 email to be completed, and it becomes an impossible task

This captures a lot of how I've been feeling lately. Thanks for sharing

With this approach I managed to get to sub-10ms start (to pid1), if you can accept a few constraints there's plenty of room!

Though my version was only tested on Linux hosts

Have played it a few times, it's really good

Working (again) on an offline translator for Android: https://github.com/davidventura/offline-translator

This week I added TTS support, which needed multiple inference pipelines, it was not easy to find models for 50 languages!

At this point, it mostly works as a crude implementation of Google translate+Google lens, but 100% offline and 100% Google-free

Niiiiiice, I've been working on something like this, but reducing linux boot time instead of snapshot restore time; obviously my solution doesn't work for heavy runtimes

Says fast, but how fast? Didn't really see any measurements

TCC is fantastic! Very hackable, easy to compile to WASM for some interesting in-browser compilation

That makes sense, I guess this was not a problem for the times I needed nolibc.

I do agree that trying to extract data/logic from linux is a pain -- I've tried a few times to extract some of the eBPF verifier handling, but end up pulling most of the kernel along.

Unikraft is cool, I still have it in my 'todo' list to play around with sometime.

Linking the app with the 'kernel' seems pretty nice, would be cool to see what that looks like for a virtio-only environment.

Just wanted to point out that the 150ms is not snapshot based, you can get <10ms for small vms (128MB ram, 2GB ram moves you to ~15ms range), for 'cold' boots.

Would it be cheating to use the kernel's nolibc?

You can do <10ms. I was working to see if I could get it under 1ms, but my best was 3.5ms

You can boot a vm without snapshots in < 10ms, just need a minimal kernel.