▲ 53 ▼ Uses for local AI? (lemmy.mtate.me.uk) submitted 2 years ago by smeeps@lemmy.mtate.me.uk to c/selfhosted@lemmy.world 55 comments fedilink hide all child comments Im using Ollama on my server with the WebUI. It has no GPU so its not quick to reply but not too slow either. Im thinking about removing the VM as i just dont use it, are there any good uses or integrations into other apps that might convince me to keep it?
[–] VeryNiiiice@sh.itjust.works 4 points 2 years ago (2 children) Which one do you use to summerize videos? permalink fedilink source parent hideshow 4 child comments replies: [–] AnUnusualRelic@lemmy.world 4 points 2 years ago (1 child) Does it work with porn videos? permalink fedilink source parent hideshow 2 child comments replies: [–] maniel@sopuli.xyz 1 point 2 years ago* asking the important question, but yeah, the plot is essential in porn permalink fedilink source parent [–] pe1uca@lemmy.pe1uca.dev 1 point 2 years ago Well, it's a bit of a pipeline, I use a custom project to have an API to be able to send files or urls to summarize videos. With yt-dlp I can get the video and transcribe it with fast whisper (https://github.com/SYSTRAN/faster-whisper), then the transcription is sent to the LLM to actually make the summary. I've been meaning to publish the code, but it's embedded in a personal project, so I need to take the time to isolate it '^_^ permalink fedilink source parent
[–] AnUnusualRelic@lemmy.world 4 points 2 years ago (1 child) Does it work with porn videos? permalink fedilink source parent hideshow 2 child comments replies: [–] maniel@sopuli.xyz 1 point 2 years ago* asking the important question, but yeah, the plot is essential in porn permalink fedilink source parent
[–] maniel@sopuli.xyz 1 point 2 years ago* asking the important question, but yeah, the plot is essential in porn permalink fedilink source parent
[–] pe1uca@lemmy.pe1uca.dev 1 point 2 years ago Well, it's a bit of a pipeline, I use a custom project to have an API to be able to send files or urls to summarize videos. With yt-dlp I can get the video and transcribe it with fast whisper (https://github.com/SYSTRAN/faster-whisper), then the transcription is sent to the LLM to actually make the summary. I've been meaning to publish the code, but it's embedded in a personal project, so I need to take the time to isolate it '^_^ permalink fedilink source parent