For anyone working with Whisper or other ASR tools, the white paper from our grant project "Increasing Accessibility of Audiovisual Content Using Whisper" is now available on the Lyrasis repository: https://doi.org/10.48609/na33-1y19
Resources gathered include stats for processing times, editing times, accuracy (word error rate), and power consumption; style guide examples for caption editors; and a project workflow for caption creation and editing.
IFLA Journal article has been published! It's part of the special issue on AI and discusses Whisper automated speech recognition, our work to make AV collections more searchable and accessible, and insights from our student caption editors on how using Whisper transforms their work. Thankful to my co-authors and our project team.
As my current "have on in the background to follow with low level attention" series I have #SexAndTheCity. Currently at the episode where Carrie meets Aleksandr Petrovsky and has dinner with him.
The waitress comes over and talks with Aleksandr, and the #captions on #Netflix read: [both speaking French]. I'm not fluent in #French, but I'm quite sure that their conversation sounded a lot more like #Russian than French. 
Which also makes a lot more sense, (Latvian-born American) Mikhail Baryshnikov's character is supposed to be Russian, and they are dining in a Russian restaurant. 
These kinds of mistakes always make me wonder how the mistake happened.
Edit: hmm, one of the later episodes has one of his assistants speaking French; I wonder if that's where the mistake came from.
Viel Forschung, wenig Umsetzung
Inklusionsarbeit ist weder leicht noch ruhmreich
Es wird im Bereich Schwerhörigkeit und Gehörlosigkeit viel geforscht und kreative Produkte entwickelt - aber es kommt selten etwas bei uns, den Menschen mit Schwerhörigkeit und Gehörlosigkeit, an. Warum eigentlich?
https://doofe-ohren.de/index.php/2025/01/15/viel-forschung-wenig-umsetzung/
@sidereal I can't comment on the time taken to edit video.
As someone who occasionally transcribes: I assure readers that the time required to transcribe can be enormous — COLOSSAL — compared to the duration of the audio or AV content that must be listened to, repeatedly.
I can not speak for @howisyourdog but I typically don't bother with content that lacks captions (subtitles). Substandard accessibility is an immediate turn-off.
My least favorite closed caption/subtitle is "[speaking in foreign language]"
It's an Italian character speaking to another Italian character, in a scene set in Italy. Can't you take a GUESS at which language it is?
Here's a hint: the language isn't "foreign" in Italy.
Do you put color information in the captions of the pictures you post here? Like "a miniature ork barbarian with green skin and red armour in front of a black background?". I would assume that it's not relevant?
Update on my attempts to make #captions work for #Jitsi:
I've heard back from the following re: no plans to support Jitsi Meet: #OtterPilot, #MeetingBaas, #ReductVideo, Fireflies
#Tactiq said it's planned, but no timeline.
Tried reaching out to #8x8 for a quote, but they never followed up...
So far, my options are to run #CaptionNinja alongside Jitsi (free), or to embed a Jitsi-as-a-Service meeting iframe on a web page and enable captions (premium).
A reunion with Theatre of the Deaf colleagues from 42 years ago prompted some thoughts about sign language interpreters, captions, and audio description:
Not sure if this is a stretch, but has anyone managed to get automated #captions (or CART) and shareable live #transcriptions working with the public #Jitsi Meet instance, even via a third-party app?
I'm not interested in self-hosting, and I'm open to paid solutions. I know that there are some services that offer a bot that you can invite into your meeting to transcribe, but the ones I've tried don't work with Jitsi (Iist in 
)
Sometimes the #Internet still has the capacity to amaze me:
They claim to be "Indexing over 1.1 billion transcripts across 1 billion videos and 69 million channels."
Psst. In case you missed it last week, we published the schedule for WordPress Accessibility Day. 24 hours of phenomenal talks - all free, on Zoom with live #captions and #ASL. Registration is open, won't you join us?
#WordPress #accessibility #a11y #conference #captioned #SignLanguage
https://2024.wpaccessibility.day/announcing-our-2024-schedule/
Does anyone have any insight into how #ClosedCaptions happen?
I've noticed issues in two shows recently, due to the strong accents and speech patterns (Northern Irish in Blue Lights on SBS, and Yorkshire in The Long Shadow on Stan).
Are the #captions generated by computer and checked by human? Are they done by the production/distribution company, or the broadcaster? #subtitles #question #accessibility
@brucelawson whisper can't just transcribe, it also can put out SRT-Files which you can import in Programms like davinci resolve to add closed captions in the video file (which time stamps and everything)!
Saved my ass some days ago. But even though it's actually quite good, you still need to (and should anyway) check the output for errors.
The Complete Guide to Captioned Videos (2019)
https://meryl.net/captioned-videos-complete-guide/
#captions #video #a11y
Y’all. I just created my first video captions, and it makes me a little giddy. Accessibility is fun.
It's pretty damning that for many shows, you have a better chance of there being Closed Captions for the Hard Of Hearing if you torrent the show than if you LEGALLY buy it from Apple TV.
busybee: fluffy rambles: Please stop using open captions https://beesbuzz.biz/blog/1723-Please-stop-using-open-captions #Accessibility #VideoEditing #Captions #YouTube #Video #Blog #Rant #A11Y
