Conversation

Notices

1. cr0n0s:~🐧📡⌨️ 🛠️ # (cr0n0s@social.tchncs.de)'s status on Friday, 17-May-2024 02:58:15 UTC cr0n0s:~🐧📡⌨️ 🛠️ #

   Algunos comandos que uso con yt-dlp

   https://github.com/yt-dlp/yt-dlp

   $ yt-dlp -F url (formato de video/audio disponibles en la url)

   $ yt-dlp -f 720p url (del anterior comando, elijes el formato 720p, para ser descargado de la url)

   $ yt-dlp -x - -audio-format vorbis url (extracción de audio en formato vorbis/ogg desde la url)

   #ytdlp

   • cr0n0s:~🐧📡⌨️ 🛠️ # (cr0n0s@social.tchncs.de)'s status on Friday, 17-May-2024 22:23:53 UTC cr0n0s:~🐧📡⌨️ 🛠️ #

     in reply to

     • Simon Willison
     • Brahn

     @Brahn wow, interesting. I'll take a look at the tools. Thanks for the information.@simon

   • Brahn (brahn@hachyderm.io)'s status on Friday, 17-May-2024 22:23:54 UTC Brahn

     in reply to

     • Simon Willison

     @cr0n0s
     I don't know if this is useful, but I use it alot.

     ```
     set -l vttfilename (yt-dlp --write-auto-sub --skip-download -o '%(id)s.%(ext)s' 'https://www.youtube.com/watch?v=IuF0GlO2Myk' 2>&1 | rg "Destination: " | rg -o '[a-zA-Z0-9_-]+\.en\.vtt')

     cat $vttfilename| ttok -m gpt-4 -t 120000 | llm -m 4o 'convert this vtt file to readable prose'
     ```

     This requires tooling from @simon; `ttok` and `llm`
     Also - this is fish shell.

     Hope it's useful!

   • cr0n0s:~🐧📡⌨️ 🛠️ # (cr0n0s@social.tchncs.de)'s status on Monday, 20-May-2024 15:58:12 UTC cr0n0s:~🐧📡⌨️ 🛠️ #

     in reply to

     • Simon Willison
     • Brahn

     @Brahn There is no doubt that when problems arise, all you have to do is be creative. Brilliant. 👍 @simon

   • Brahn (brahn@hachyderm.io)'s status on Monday, 20-May-2024 15:58:13 UTC Brahn

     in reply to

     • Simon Willison

     @cr0n0s @simon I just realized how unhappy i was with just using `ttok` to fit it into the model. I wrote this python script to strip out garbage.

     I went from 100k+ tokens to `25626` and no loss of context!