Thanks for the tip on the GPU! I live in an area where power is relatively cheap, so I'll probably go for the 3060. I really wish some of these would work better with AMD since their drivers seem to be more Linux-Friendly these days.
If I get something going, I'll share for sure!
My opinion is that your spouse will have to get rid of any other hobby related stuff. If you're a fisherman, she's going to have to find something to do with all the tackle, boat/s, gear.
I know a guy that was a woodworker who had a shop full of well over $20k worth of tools. Poor guy got cancer and died, and his wife had to try to get rid of all of it. Luckily she had some of his woodworking friends who helped her price and sell the stuff. (I got a pretty nice used planer out of the deal)
The free version of Otter.ai limits you to 30 minutes per conversation, 300 total monthly transcription minutes. "Pro" moves you up to 90 minutes per conversation with 1200 total minutes for $8.33/month (billed annually). "Business" is $20/month with 4 hours per conversation and 6000 total minutes. They have an "Enterprise" version, but it is one of those "call for a quote" things.
The Pro is somewhat reasonably prices, but the 90 minutes per meeting limit is a wall I would bounce up against pretty often. Hard to justify the $20/month for me when a couple years of service is about the same price as the GPU I've been wanting anyway. Plus, the GPU would be a business expense now, right? :)
Thank you! I'll make see if I can string together a few things to come up with my own homebrew version of these services. Honestly, for what they're charging I think I can justify a new dedicated GPU. I've got a few other dockers/services which could take advantage of it anyway, so maybe this is the excuse I've been needing to pull the trigger on that purchase.
Thanks for the heads up on Danswer!
Sure!
For work I attend a lot of meetings, both in person and online. The service takes a recording of the meeting/phone call/etc, transcribes it, identifies the people who were talking and then feeds it into a "ChatGPT" style AI. It then gives meeting notes automatically and lists action items assigned to each attendee along with other pertinent information, like due dates. You can also continue to "chat" with the AI regarding anything to do with the meeting. I often will asked it to expound on various topics, write emails to participants following up on items, give me pertinent information that was shared like emails, phone numbers, etc. You are also able to go back and listen to the meeting along with the transcription. If it was a video meeting, it records the video so you can see what was being presented at the same time. (I think there's some opportunity for OCRing power point slides too, but these services aren't doing that yet)
One specific example was a conversation I had with a customer regarding another company we worked with mutually. The customer went into great detail about their issue with the other company and asked if I could write an email to that company to try and help solve their problem. I fed the recording of the phone call into the AI and simply told it to "write the email referenced in the conversation" and it wrote out a pretty good email with a lot of detail that was shared by the customer in it. A couple of tweaks and I was able to copy and paste it right into my email software and send it.
There's some other features the software has that I personally don't find as useful, like automatic sharing of meeting minutes/notes. My two biggest issue with these services is that they are charging somewhere in the neighborhood of $20 US per month for an amount of "minutes" of meetings. Also, they are taking all of your meeting data and doing who knows what with it? They do meet all the European Union and California privacy standards according to their site, but we're all here on a decentralized self-hostable community, so I probably don't need to expand on my issues there :)
Even if there was just a good "ChatGPT" style AI I could self-host, I could probably transcribe the recordings somehow myself.
Loved the UPS article itself. If you wanted to level it up one more time, you could do something like this: https://hackaday.com/2023/07/31/automatic-transfer-switch-keeps-internet-online/
It is a automatic transfer switch, so that in the case of a UPS failure, the power can be transferred to a wall outlet fast enough that you shouldn't experience an outage.
I told my wife when I die, she's just going to have to throw it all away and start over.
We have separate email accounts and she knows how to get into my Keepass, so she should be able to get into whatever she needs to. I now have a daughter who is becoming interested in how these things work, so I'm hoping to slowly start training/handing off to her.
You can get someone knowledgeable like an electrician to just change the outlet itself to whatever is best.
"220 V" is the "nominal" voltage. All voltages fluctuate depending on all sorts of factors, but should stay within a certain range of nominal. In the USA most utilities follow the ANSI C84 Voltage standard. 220 V is what electricians refer to it as. Your utility probably calls it "240 V".
Do you guys have a docker image or something that I could put on my homelab server?
I have a Nextcloud server that I setup (before Immich was a thing. I'm also running it now, but not using it for photo backup). I have accounts for my immediate family and all of our phones are setup to use the Instant Upload feature to back up photos.