• 1 Post
  • 856 Comments
Joined 2 years ago
cake
Cake day: July 14th, 2023

help-circle
rss


  • Is your goal to create things that can be published or used in a project, or to create audiobooks for yourself to listen to?

    For voiceovers for text, I use Kokoro Fast API, which has a web frontend. The frontend is only compatible with Chromium browsers on desktop or Android, which sucks as my daily driver is Firefox and an iPhone (there are workarounds in the thread) but it supports voice mixing, speed changes, etc… It also has an issue where it keeps the models (about 3GB) in memory; I keep the CPU version loaded normally and swap to the GPU version if I need it to be faster. If you want something similar for Bark, check out Bark-GUI.

    I’ve also dabbled a bit in some TTS features that have Comfy nodes, though at this point mostly just in terms of getting them set up. For my purposes thus far Kokoro has been fine (and I prefer the FastAPI project over the Comfy nodes for most of my uses), but I’ve found nodes for Kokoro, Dia, F5 TTS, Orpheus, and Zonos.

    Autiobooks and audiblez both look promising. A few weeks ago, I used the Kokoro FastAPI web frontend to create an audiobook for an ebook I worked on that used entirely self-hosted AI generation for the outlining and prose. Audiblez, which I found about like two days after that, looks like it would have simplified that process substantially. Still, I’d personally like something more like an audiobook studio, where I can more easily swap voices back and forth, add emotions, play with speed on a more granular level, etc… I’m thinking about building something that contains that at some point myself, but it’ll be a minute - hopefully someone else will beat me there.

    I posted a comment here a few weeks back on a similar topic. I’ve since used OpenReader-WebUI and like it, though that’s not for producing audiobooks, but for a read-along experience. Reproducing the comment below in case it’s helpful for you:

    If you want to generate audiobooks using your own / a hosted TTS server, check out one of these options:

    • OpenReader-WebUI - this has built-in read along capability and can be deployed as a PWA that can allow you to download the audiobooks to your phone so you can use them offline
    • p0n1/epub to audiobook
    • ebook2audiobook If you don’t have a decent GPU, Kokoro is a great option as it’s fast enough to run on CPU and still sounds very good. If you’re going to use Kokoro, Audiblez (posted by another commenter) looks like it makes that more of an all-in-one option. If you want something that you can use without an upfront building of the audiobook, of the above options, only OpenReader-WebUI supports that. RealtimeTTS is a library that handles that, but I don’t know if there are already any apps out there that integrate it. If you have the audiobook generation handled and just want to be able to follow along with text / switch between text and audio, check out https://storyteller-platform.gitlab.io/storyteller/

  • Your comment wasn’t in a meta discussion; it was on a post where they were venting about people complaining about them having a women’s only space. There was certainly no indication that the regular community rules didn’t apply, nor any invitation for men to comment.

    Commenting that it’s hostile for them to have a women’s only space might be ironic, but couldn’t possibly be good faith, in that context. And if the same mod banned you from multiple communities, then either it was out of line and you could appeal it, or it was warranted due to the perceived likelihood of you causing problems in those other communities and the perceived low likelihood of you contributing anything of value to them.

    Even now, you’re acting like the mod(s) banned you because of her / their emotions. You don’t see how that’s misogynistic?

    It makes logical sense for bad actors to be preemptively banned. Emotions have nothing to do with it.


  • Right now I have Ollama / Open-WebUI, Kokoro FastAPI, ComfyUI, Wan2GP, and FramePack Studio set up. I recently (as in yesterday) configured an API key middleware with Traefik and placed it in front of Ollama and Comfy, but currently nothing is using them yet.

    I’ll probably try out Devstral with one of the agentic coding frameworks, like Void or Anon Kode. I may also try out one of the FOSS writing studios (like Plot Bunni) and connect my own Ollama instance. I could use NovelCrafter but paying a subscription fee to use my own server for the compute intensive part feels silly to me.

    I tried to use Open Notebook (basically a replacement for NotebookLM) with Ollama and Kokoro, with Kokoro FastAPI as my OpenAI endpoint, but turns out it only supported, and required, text embeddings from OpenAI, so I couldn’t do that fully on my local. At some point, if they don’t fix that, I’m planning to either add support myself or set up some routes with Traefik where the ones OpenNotebook uses point to the service I want to use.

    ETA: n8n is one of the services I plan to set up next, and I’ll likely end up integrating both Ollama and Comfy workflows into it.



  • I think the best way to handle this would be to just encode everything and upload all files. If I wanted some amount of history, I’d use some file system with automatic snapshots, like ZFS.

    If I wanted to do what you’ve outlined, I would probably use rclone with filtering for the extension types or something along those lines.

    If I wanted to do this with Git specifically, though, this is what I would try first:

    First, add lossless extensions (*.flac, *.wav) to my repo’s .gitignore

    Second, schedule a job on my local machine that:

    1. Watches for changes to the local file system (e.g., with inotifywait or fswatch)
    2. For any new lossless files, if there isn’t already an accompanying lossy files (i.e., identified by being collocated, having the exact same filename, sans extension, with an accepted extension, e.g., .mp3, .ogg - possibly also with a confirmation that the codec is up to my standards with a call to ffprobe, avprobe, mediainfo, exiftool, or something similar), it encodes the file to your preferred lossy format.
    3. Use git status --porcelain to if there have been any changes.
    4. If so, run git add --all && git commit --message "Automatic commit" && git push
    5. Optionally, automatically craft a better commit message by checking which files have been changed, generating text like Added album: "Satin Panthers - EP" by Hudson Mohawke or Removed album: "Brat" by Charli XCX; Added album "Brat and it's the same but there's three more songs so it's not" by Charli XCX

    Third, schedule a job on my remote machine server that runs git pull at regular intervals.

    One issue with this approach is that if you delete a file (as opposed to moving it), the space is not recovered on your local or your server. If space on your server is a concern, you could work around that by running something like the answer here (adjusting the depth to an appropriate amount for your use case):

    git fetch --depth=1
    git reflog expire --expire-unreachable=now --all
    git gc --aggressive --prune=all
    

    Another potential issue is that what I described above involves having an intermediary git to push to and pull from, e.g., running on a hosted Git forge, like GitHub, Codeberg, etc… This could result in getting copyright complaints or something along those lines, though.

    Alternatively, you could use your server as the git server (or check out forgejo if you want a Git forge as well), but then you can’t use the above trick to prune file history and save space from deleted files (on the server, at least - you could on your local, I think). If you then check out your working copy in a way such that Git can use hard links, you should at least be able to avoid needing to store two copies on your server.

    The other thing to check out, if you take this approach, is git lfs. EDIT: Actually, I take that back - you probably don’t want to use Git LFS.












  • I think the better question than “Does the experience system sound like it has potential,” then, is “Does the overall concept / system have potential?”

    My gut is probably, but it depends a lot more on what you’re willing to put into it and what you want out of it. What’s your metric for success? If it’s something you want to run yourself and to share online to have a few groups use it, then that’s a lot more achievable than being able to get a publishing deal, for example. And in-between, publishing on drivethrurpg or something similar, at a nominal cost (like $2-$5), would take more effort than the former and less than the latter; and the higher the cost and the higher the number of players you’d want, the higher the effort you need to put in (and a lot of that isn’t just in system building, but in art, community building, marketing, etc.).

    From what you’ve shared, it sounds like an interesting system. I could especially see it working in an academy setting where grinding skills to be able to pass practical exams is one of the players’ goals. I also could see it working well by a loosely GMed play by post system, with the players self-enforcing (or possibly leveraging some tools built into the site to track resource pools, experience, rolling, etc.), though I haven’t played in a forum game myself, so I might be way off-base.

    Did your system have classes or was it completely free-form in terms of gaining access to those skill trees?


  • I run a Monster of the Week game and my players get experience throughout sessions, as well as at the end. The mechanics are basically:

    • It takes 5 experience points to level up.
    • If you fail a roll, you get an experience point.
    • If you level up, you get the benefit immediately.
    • At the end of the session, everyone gets 0-2 experience points.

    I think other PbtA (Powered by the Apocalypse - systems inspired by Apocalypse World) systems do something similar.

    I grew increasingly frustrated with the system of only distributing advancement/experience points at the end of a session.

    Isn’t the simple fix to this to just distribute experience points as soon as they’re earned?

    At some point, I started to divise a play system that relied on a split experience atribution system, with players being able to automatically rack experience points from directly using their skills/habilties, while the DM would keep a tally of points from goals/missions achieved, distributable at session end.

    Your system sounds like the way that skill-based video game RPGs (Elder Scrolls games and Arcanum come to mind) handle experience.

    In a lot of games I’ve played, I’d rather get experience for in-game accomplishments immediately and to be able to train skills like this during downtime - generally between games.

    To those with more experience in TTRPGs: would this be feaseable? Or enticing? Interesting?

    I could see people being interested in it. You get instant gratification and a bit of extra crunchiness. A lot of players enjoy that.

    With the right skill system I could see this being useful. My main concern is that if you put this on top of a system with relatively few skills, it could encourage people to game it by grinding. There are ways to mitigate that, though.

    In a system with fewer skills, instead of just being experience points, the “currency” you earned this way could be used for temporary power ups related to the skill in question.

    You could also limit it so you only rewarded players for story-related tasks.


  • Copied from the post:

    You may have seen reports of leaks of older text messages that had previously been sent to Steam customers. We have examined the leak sample and have determined this was NOT a breach of Steam systems.

    We’re still digging into the source of the leak, which is compounded by the fact that any SMS messages are unencrypted in transit, and routed through multiple providers on the way to your phone.​

    The leak consisted of older text messages that included one-time codes that were only valid for 15-minute time frames and the phone numbers they were sent to. The leaked data did not associate the phone numbers with a Steam account, password information, payment information or other personal data. Old text messages cannot be used to breach the security of your Steam account, and whenever a code is used to change your Steam email or password using SMS, you will receive a confirmation via email and/or Steam secure messages.​

    You do not need to change your passwords or phone numbers as a result of this event. It is a good reminder to treat any account security messages that you have not explicitly requested as suspicious. We recommend regularly checking your Steam account security at any time at ​

    https://store.steampowered.com/account/authorizeddevices

    We also recommend setting up the Steam Mobile Authenticator if you haven’t already, as it gives us the best way to send secure messages about your account and your account’s safety.