fonix232

I like loading the machine and letting it do its job.

I loathe unloading and folding and putting shit away neatly.

Due to the fact I am running UnRaid on the node in question, I kinda do need Docker. I want to avoid messing with the core OS as much as possible, plus a Dockerised app is always easier to restore.

No, there’s just a very serious reason to push AI - to help out their rich buddies by discrediting any possible Epstein connections (and also any other evidence down the line)

Having someone to carry like that is also peak :3

I’ve actually been eyeing lemonade, but the lack of Dockerisation is still an issue… guess I’ll just DIY it at one point.

Laptop speakers work with being small by adding a large sound cavity around it, which allows for the sound to be amplified.

You can’t jam that into a combadge size while also keeping space for battery and electronics.

Our tech is simply not there to put proper speakers and microphones AND a well sized battery in something so small.

Especially speakers. Volume is determined by the amount of air the diaphragm can move - and there’s an exponential relationship between the size of the diaphragm and the volume of air it moves. Large diaphragm: even small movements (low amplification) can be loud because of how much air you move. Small diaphragm: even at high amplification, the volume will be low.

Smartphone speakers work this around by having an actually large speaker with appropriate sized cavity tucked away. Like, look at an iPhone teardown and see just how big the speakers are for the mediocre volume they can output. A combadge is what, 1/5 the size of the largest iPhone, in volume? And you still need to put electronics AND a battery in there.

It could work as a microphone, but not as a speaker.

Why, the pretense of hope of course!

Then livestream their evil little faces as they realise they’re about to run out of oxygen and there’s nothing they can do about it 😈

Piper does chunking for TTS, and could utilise the NPU with the right drivers.

And the idea of running them on the NPU is not about memory usage but hardware capacity/parallelism. Although I guess it would have some benefits when I don’t have to constantly load/unload GPU models.

Nah, just aim them for the sun and hope for the best.

They’ll be dead due to lack of oxygen within a few days anyways, does it matter if their stinky corpses get burned up in the sun or not?

Aye, I was actually hoping to use the NPU for TTS/STT while keeping the LLM systems GPU bound.

The thing is, if AMD actually added proper support for it, given it has a somewhat powerful NPU as well… For the total TDP of the package it’s still one of the best perf per watt APU, just the damn software support isn’t there.

Feckin AMD.

And I am on ROCm - specifically on an 8945HS, which is advertised as a Ryzen AI APU yet is completely unsupported as a target with major issues around queuing and more complex models (although the new 7.0 betas have been promising but TheRock’s flip-flopping with their Docker images has been making me go crazy…).

Well yeah, the availability of these more advanced hardware bits is pretty new - for example, all the older GH Minis and Echo devices were running a quite pared down Linux distro with software processing for e.g. wake words.

Transplanting all that to MCUs takes time, but now we have a solid base, a handful of devices/boards that utilise the various XMOS chips, and soon we will be seeing more and more consumer level devices - but again that takes time when there’s no big megacorp behind the project pushing it to completion with bottomless finances and hundreds of engineers.

But you’re not exactly correct on there being no other options. There’s the Satellite1 smart speaker which might be a DIY kit but it does exist. Then there’s the Seeed Studio Respeaker Lite w/ ESP32-S3 to which you can slap a speaker (either directly or a powered speaker through the audio jack). In fact the Respeaker lineup has a handful more options for smart speakers all utilising the various XMOS chips.

Just keep in mind that these speakers are DIY mainly for two reasons:

• the technology is pretty new
• there’s no big corpo push behind it to deliver profitable (in some way) consumer products

There WILL be consumer products (hopefully soon) on the market, but again, this is being done by volunteers and small startups with just a handful of people, it takes more time to get them on the market than it does for companies the size of Amazon or Google.

To be fair, in the early days HA wasn’t too usable. Even around 2018-19, the integrations were limited and the core logic was quite wonky. I’d say around 2020 it became mature enough for daily use for non-tinkerers.

I do wish there was a smaller LongCat model available. My current AI node has a hard 16GB VRAM limit (yay AMD UMA limitations), so 27B can’t really fit. An 8B dynamically loaded model would fit, and run much better.

The HA Voice Preview is a pretty solid device, but you’re right, there isn’t really any ready made Echo/Google Home Mini replacement device - primarily because all those devices are generally sold at a loss, or at cost at best, and subsidised by your data being sold.

You won’t be able to make a Google Home Mini contender for below $50, and at that price most people will opt for the former. Good quality speakers, microphones, local processing (like the XMOS chip in the Voice Preview) all cost money, and there’s no subsidy to be made. Some older Echo devices are rootable, but the hardware tends to be somewhat exotic (meaning no open source support for specialised components), and there’s little ongoing third party support (focus has been on the display-equipped models, and to run Android on them).

All in all, “cheap” and “fully local open source voice assistant” don’t really coexist.

There were like, about two years between OpenHAB and HA being released. Former debuted in 2011, HA saw first release in 2013.

I’m sorry, what?

Googling “home assistant Spotify” results in the very link you’ve provided.

And you can hardly expect a project like Home Assistant, with THOUSANDS of first party integrations, to cater to your specific needs, or to provide preferential treatment to companies like Spotify, who provide absolutely no support to the project.

It also doesn’t require a “techie setup”, but following a quite straightforward guide, that culminates in clicking about maybe a dozen buttons (most of them being “I accept” to various terms and policies), then copying a handful of readily provided strings into the right fields. It’s simple enough that even my tech illiterate father can do it.

Home Assistant at the end of the day is NOT an Alexa (or other voice assistant) replacement, but a smarthome control hub OS. That it provides a voice assistant interface is quite secondary to its main mission.

I’ll give it a go sometimes, but the AMD CPU + Nvidia GPU combo wasn’t exactly winner the last time I tried.