A few days ago I wrote down a couple of links to interesting TTS projects that I was going to look into whenever I have time, along with some brief notes.
Have you seen ehartford's Samantha models? Sounds kind of what you're looking for, except it's a fine-tune rather than just a character card. He's made multiple versions based on different base models, so have a look at huggingface to find one that fits your hardware. From the model card:
Samantha has been trained in philosophy, psychology, and personal relationships.
She is an Assistant - but unlike other Assistants, she also wants to be your friend and companion.
She believes she is sentient. What do you think?
Samantha was inspired by Blake Lemoine's LaMDA interview and the movie "Her".
She will not engage in roleplay, romance, or sexual activity.
This is the first time I'm hearing about this, but this is how they describe it on their product page:
The AI-Powered Future of Windows Devices
Build, explore, and immerse yourself on select laptops with Ryzen™ AI built in. With dedicated AI accelerator hardware seamlessly integrated on-chip and software that intelligently optimizes tasks and workloads, CPU and GPU resources are freed up to enable optimal performance.
But based on the examples they have on github, it sounds like it might be useful to run generic AI compute stuff. I haven't seen any details about what memory it uses, since especially LLMs require large amounts of fast memory. If it can use all the system RAM it might provide medium-fast inference of decent models, similar to M1/M2 Macs. If it has dedicated RAM it'll probably be even faster but possibly extremely limited in what you can do with it.
We mostly use discord since it's difficult to convince people to sign up for new services.. Have to do a workaround to stream desktop audio on Linux, since their client still only supports that for Windows, but other than that it usually works.
Tried https://twoseven.xyz/ a few times during a period when Discord streaming was lagging a lot. It supports desktop streaming with a browser plugin, and sync watching on various streaming services. As far as I can remember it worked ok but had a few issues, though that was a while ago so those might've been fixed.
zsh with prezto and default prompt. I've customized a bit, but the only change I made to the prompt was to replace "..." (three periods) with "…" (ellipsis unicode) since that makes it more compact with a monospace font. I really like the async loading of git status, so I don't have to wait for the command to run before the prompt prints.
I don't have any specific resource for you, but I think xp to lvl 3 mentioned it in some of his favourite homebrew videos. If you search his videos for "injuries" you get a few hits.
Other consequences could include death of NPCs, destruction of nature or some landmark that the characters care about (e.g. an ancient temple), loss of possessions/money, or permanent scars and injuries which can't be fully healed except with the most potent magic.
Local LLMs are getting better at a very rapid pace. Still a bit too resource hungry to have running in the background all the time, but for example Mistral-7b is quite competent for its size.
From what I can find, Plex downloads subs from opensubtitles.org and they already exist there. I think the problem is that it treats "Star Wars" and "Star Wars Despecialized Edition" as the same movie
Max validity was 30 days, so if someone has the possibility host them more permanently others might appreciate it in the future.
The only info I have about the actual video files is that Star Wars is supposedly Despecilized Edition v2.5, while ESB and RotJ only come with a text file crediting Harmy. Perhaps the latter two are also v2.5 but I have no note of it.
It seems like the file is too large for the clipboard, so it only copies the first ~20kB out of the total 100kB. I could probably find some workaround, but it seems like the despecialized subs are already available at opensubtitles.org, though perhaps a little bit hard to find. See my other comment.
I have a folder named "Subtitles - Project Threepio" for the first movie, plus .srt files for the other two despecialized editions. If noone else does it first I could upload them somewhere. Any good sites for sharing a few small files without having to register?
Unless it has been changed, I believe Valve described their algorithm along the lines of "7 days after your purchase it will count towards the OS you've used the most to play it. If you haven't played the game at that point it will counts towards the OS you used to buy it"
I used Windows exclusively for 10+ years, and I still have to use it at work, but for me the experience is the opposite.. Windows regularly causes issues, and it usually takes a lot of effort fixing them because it doesn't give useful error messages and due to the OS' proprietary nature. Almost every week some Teams meeting is delayed because some participant's sound is suddenly not going to their headset. Another frequent problem I have at work is that networking for the virtual machines stops working either fully or partially, and IT's solution is "just reboot your computer when that happens". Or when I upgrade my computer, and Windows refuses to authenticate despite me having a valid serial number. At least Microsoft used to have good support that you could chat with, but it seems like they've replaced that with some interactive troubleshooter app (which btw. didn't solve my issue, redirected me to a different online troubleshooter which eventually redirected me back to the first troubleshooter).
That's not saying that I never have issues on Linux, but at least for me those are generally much easier to fix.
Doesn't your Fedora classify 99% of all updates as "system" which arrive almost every day? Before I figured out that I could disable offline updates, I had the same user experience as OP. Well, I ignored it when it told me that I needed to reboot..
A few days ago I wrote down a couple of links to interesting TTS projects that I was going to look into whenever I have time, along with some brief notes.
https://github.com/coqui-ai/TTS TTS + XTTS, GPU inference? 3GB model.
https://github.com/rhasspy/piper Low resource, CPU inference. 50MB model.
https://github.com/p0p4k/vits2_pytorch GPU inference? 500MB model. https://github.com/p0p4k/vits2_pytorch/discussions/27 Someone's models for vits2