Tech behemoth OpenAI has touted its artificial intelligence-powered transcription tool Whisper as having near “human level robustness and accuracy.”

But Whisper has a major flaw: It is prone to making up chunks of text or even entire sentences, according to interviews with more than a dozen software engineers, developers and academic researchers. Those experts said some of the invented text — known in the industry as hallucinations — can include racial commentary, violent rhetoric and even imagined medical treatments.

Experts said that such fabrications are problematic because Whisper is being used in a slew of industries worldwide to translate and transcribe interviews, generate text in popular consumer technologies and create subtitles for videos.

More concerning, they said, is a rush by medical centers to utilize Whisper-based tools to transcribe patients’ consultations with doctors, despite OpenAI’ s warnings that the tool should not be used in “high-risk domains.”

0 points

Oh word?

permalink
report
reply
11 points

AI does not mean Artificial Intelligence, it means Assumed Intelligence.

permalink
report
reply
71 points

LLMs in medicine. What could go wrong?

permalink
report
reply
10 points

Whisper isn’t a large language model.

It’s a speech to text (STT) model.

permalink
report
parent
reply
6 points

Which has the same concept as the LLM under the hood, hasn’t it?

permalink
report
parent
reply
7 points

This isn’t a Large Language Model, it’s a Chonky Linguistic Algorithm.

permalink
report
parent
reply
80 points
*

Some examples

In this example, the speaker said, “as the um, the, her father dies not too long after he remarried….” while the program transcribes that as " It’s fine. It’s just too sensitive to tell. She does die at 65….”

In this example, the speaker said, “and after she got the telephone he began to pray” while the program transcribes that as “I feel like I’m going to fall. I feel like I’m going to fall, I feel like I’m going to fall….”

permalink
report
reply
59 points
*

Wow, that’s bad. I thought it would be more of a “confusing a sentence for a similar sounding one” type thing but from the above and the article it’s just generating semi-believable text and sticking them into the transcriptions.

permalink
report
parent
reply
25 points

It’s actually extremely good at figuring out confusing text. It gets weird when the audio quality is bad.

I use it for generating subs for obscure movies.

permalink
report
parent
reply
7 points

No one is good with bad audio. My wife did some transcription work for a little while, it can be pretty painful, especially for doctors, and all the medical terms.

permalink
report
parent
reply
3 points

Sounds less like transcribing word for word, and more like attempting to summarize and parse meaning on the fly. AIS have notoriously little grasp on reasoning and logic, so it’s interesting how the output holds up in a court of law.

permalink
report
parent
reply
15 points

This one was wild:

In an example they uncovered, a speaker said, “He, the boy, was going to, I’m not sure exactly, take the umbrella.”

But the transcription software added: “He took a big piece of a cross, a teeny, small piece … I’m sure he didn’t have a terror knife so he killed a number of people.”

From picking up and object to mass murder lmao. Not even close!

permalink
report
parent
reply
1 point

But it gets the spirit right

/s

permalink
report
parent
reply
22 points

Microsoft teams has some automatic transcript capabilities that are so hilariously bad, it’s hard to believe Microsoft released it.

I guess they use the same service.

permalink
report
reply
1 point

It’s super hit or miss, odds are it’s using azure though and not just running a model locally.

permalink
report
parent
reply
1 point

The last transcript I’ve seen it guessed the wrong language and literally didn’t get one word right.

permalink
report
parent
reply

Technology

!technology@lemmy.world

Create post

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


Community stats

  • 17K

    Monthly active users

  • 12K

    Posts

  • 542K

    Comments