You can, but you need their app.

That isn’t something I’m going to do, so I tag manually instead.

I know, thats why I’m asking a question.

Well, perfect use case for the test immich instance!

I’ve got a few day trips recently that will make for good tests for over the weekend.

Those changes happened in less than an hour?

I’m a bit confused because your last paragraph asks direct questions that are already addressed.

The immich service connection.with writeback is awesome!

My kids have some dinky little digital cameras with no GPS or WiFi or anything, just writes photos locally to microsd, so obviously no location data. I use my phone, sure, but when traveling I’ll use my DSLR that also has no GPS (OK it does have WiFi, but I don’t use it).

Which turns into me tagging every time we get back from somewhere.

Going to give that immich link a try!

Its relatively new (past 6 weeks or so?) due to an influx of projects and a lot of repeat questions, and after some community discussions its where things landed.

No worries, just clarifying, which I’ll need to add into the rules as well somehow…

even if you are promoting someone else’s project/app.

To correct you on this - ifyou are linking someone else’s project/app, it would be entirely impossible to require a disclosure. A tag is a nice-to-have depending on how visible those elements are, but the paid/30 day account age for f/loss would still apply.

I suspect I’ll need to clean up the language some if this is the takeaway.

Aside from “local model”, you might see things like whisper.cpp, llama.cpp, ollama, or “OpenAI compatible endpoint”, or a reference to getting models from HuggingFace (you can think of it like github for llm’s - its more and less, but accurate enough for what we’re talking about here).

whisper.cpp is a c++ implementation of whisper (ASR as mentioned), llama.cpp is a high performance and lightweight tool to support llm/llm inference, ollama is a very user friendly way to do the same, and OpenAI compatible endpoint is just using the protocol for communication, so you can point the client at llama.cpp or similar running on the same machine or another you have access to.

Most things with an extemely tight purpose like this (like listening for some birds singing) will use much leaner models, and may be able to run even from a phone.

Audio processing by ai can absolutely happen on a pi.

As an example, whisper.cpp is a high performance speech recognition model, and it does a great job. The biggest version of it as a model requires less than 5GB to live fully in memory, the large model at about 1.5billion parameters, and it works great even CPU only.

The one used most often is small, which has about 244million parameters, and needs about a gig of ram and nothing more.

For a pi 5, usually the base or tiny model are used. Small could be used in most scenarios, but tiny and base are able to run real-time.

So it depends for how local - sometimes its all self contained and can do just fine on a pi, sometimes its local in that it needs an LLM endpoint to hit, but that can be running on another system entirely.

It would really depend on the project for how/where/why for a definition of local.

Feedback or questions is appropriate. We don’t need to come in abrasive, and you didn’t need chatgpt to ask a followup, so we don’t need to be antagonistic.

Choosy self-hosters choose Debian.

That said, I don’t recommend hosting software at the bare metal level - use VMs or containers. Far easier to manage and isolate.