OK. I'm at wit's end attempting to convince Google's LLM to pronounce an English name correctly.

Submitted ⁨⁨1⁩ ⁨day⁩ ago⁩ by ⁨Powderhorn@beehaw.org⁩ to ⁨technology@beehaw.org⁩

Seriously, 15 times is my limit on correcting an LLM.

The name in question? Rach. Google absolutely cannot pronounce it in any other way than assuming I was referring to Louise Fletcher in the diminutive.

Specifying “long a” did nothing, and now I’m past livid. If you can’t handle a common English name, why would I trust you with anything else?

This is my breaking point with LLMs. They’re fucking idiotic and can’t learn how to pronounce English words auf Englisch.

I hope the VCs also die in a fire.

source

Comments

Sort:hotnew top

jarfil@beehaw.org ⁨1⁩ ⁨day⁩ ago
There is a reason why people keep asking “How do you spell it?” when being told a name in English. The counterpart is, “How do you pronounce it?”.

Even with “long a”, I still can’t tell how would you want to pronounce “Rach”. I can come up with 4 different pronounciations right now: “Ra-ah-ch”, “Ra-ah”, “Ra-sh”, “Ra-kh”.

source
- AbelianGrape@beehaw.org ⁨1⁩ ⁨hour⁩ ago
  Given that OP says this is a common English name (it’s not), I have to imagine that they’re referring to the common short form of Rachel. Pronounced as just the first syllable.
  
  source
- TimLovesTech@badatbeing.social ⁨1⁩ ⁨day⁩ ago
  I feel like at least with American english people have taken a lot of liberties in how they spell a name and then want it pronounced.
  
  And I first read it as Ra-sh, but also could see it as Ray-sh.
  
  What did you do to “teach it”?
  
  source
masterofn001@lemmy.ca ⁨1⁩ ⁨day⁩ ago
Short for Rachel?

source
- datavoid@lemmy.ml ⁨1⁩ ⁨day⁩ ago
  How do they differ? It’s literally just saying Rachel without the ‘el’.
  
  source
  - masterofn001@lemmy.ca ⁨22⁩ ⁨hours⁩ ago
    You can listen on that site.
    
    One is RAYch The other is RAHch
    
    source
    -> View More Comments
PonyOfWar@pawb.social ⁨1⁩ ⁨day⁩ ago
Did you try spelling it with phonetics?

source
- Powderhorn@beehaw.org ⁨19⁩ ⁨hours⁩ ago
  I know IPA (the linguistic term, not the beer … OK, I also know the beer, but that’s not important right now) … and, yeah, I tried that, but on a laptop without a numpad, it’s a bit of a slog.
  
  What was maddening was the LLM got it right somewhere around 10% of the time after I corrected it. This was a voice conversation, so every time I corrected it, that should have been clear data. Aren’t these systems simply supposed to be pattern recognition? How is it outputting wildly different pronunciations (N>5) with constant inputs?
  
  source
  - TehPers@beehaw.org ⁨16⁩ ⁨hours⁩ ago
    The modeld themselves are nondeterministic. Also, they tend to include a hidden (or sometimes visible) random seed that gets input into the models as well.
    
    source
    -> View More Comments
Hirom@beehaw.org ⁨16⁩ ⁨hours⁩ ago
I quikly gave up on correting those bots. Either you’re lucky and made a prompt that induced it to generate a decent answer. Or you’re not, and there’s no point on correcting it. In that case you’re better off doing whatever you were going to do without a LLM.

source