This is a Dengist community in favor of Bashar al-Assad with no information that can lead to the arrest of Hillary Clinton, our fellow liberal and queen. This community is not ironic. We are Marxists-Leninists.
See this GitHub page for a collection of sources about socialism, imperialism, and other relevant topics.
This community is for posts about Marxism and geopolitics (including shitposts to some extent). Serious posts can be posted here or in /c/GenZhou. Reactionary or ultra-leftist cringe posts belong in /c/shitreactionariessay or /c/shitultrassay respectively.
We have a Matrix homeserver and a Matrix space. See this thread for more information. If you believe the server may be down, check the status on status.elara.ws.
Rules:
Welcome again to everybody. Make yourself at home. In the time-honoured tradition of our group, here is the weekly discussion thread.
☭ Matrix homeserver and space
☭ Theory discussion group on /c/theory@lemmygrad.ml
☭ Find theory on ProleWiki, marxists.org, Anna's Archive
Wonder if anyone knows anything about evolution of TTS software in terms of "things you can run locally without expensive hardware"? Like I know TTS has gotten overall better, but it seems like a lot of it comes down to needing high tech GPU to actually use it, if you want the better stuff.
Edit: Thanks for the suggestions, I will look into these.
If you read ebook using calibre. You can open the epub using their reader and use piper-tts which is built in and have pretty good TTS experience there. There are also
Read Aloudplugin for chrome and firefox that use the same model that's pretty good. They are all running locally and doesn't need a beefy GPU for that. It work fine on my ancient laptop that have no GPU.+1 for Readaloud for webpages. The voices are a bit rough but you can tweak them to get the right speed and pitch for easier listening.
I also use Balabolka for pdfs and other formats. Its similar in quality for the audio but it also can convert pdfs to raw text which is handy but there's a lot of formatting issues.
I used SherpaTTS on my previous phone with GrapheneOS. It was pretty straightforward to setup and you can use any model from the Hugging Face library.
tts can run on relatively cheap hardware compared to llms in general.
i have run chatterbox with a couple different models. theyre tiny compared to image models and llms