Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #25940

J

Jordan Darefsky

Personal blog · jordandarefsky.com/blogaiprogramming

Jordan Darefsky writes blank, a personal blog at jordandarefsky.com about ai and programming. Since 2025, 3 different Hacker News readers have linked it 3 times. It is still writing: the last post was on 2025-11-20, and you can follow it by feed.

Visit the blog
3mentions?
3HN people?
2025–2025first – last linked?

Too few sampled comments (3) to say how often HN recommends it.?

Why HN links it

HN readers link Jordan Darefsky's Parakeet post, about a model fine-tuned from Whisper. In a Dia TTS thread, commenters cite it for the model architecture and licensing points.

Summarised by Claude from a sample of 3 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

# A simple, whitespace theme for academics. Based on [*folio](https://github.com/bogoli/-folio) design.

Most-linked posts?

  1. /blog/2024/parakeet/
    2 people · 2 mentions · first linked 2025-04-22

What Hacker News says?

  1. Well, this for one, about Parakeet: > We plan to release our fine-tuned whisper models and possibly the generative model (and/or future improved versions). The generative model would have to be released under a non-commercial license due to our datasets. https://jordandarefsky.com/blog/2024/parakeet/

    Comment linking /blog/2024/parakeet/

    on “Show HN: Dia, an open-weights TTS model for generating realistic dialogue”
  2. It’s not just you. The speedup is an artefact of the CFG (Classifier-Free Guidance) the model uses. The other problem is the speedup isn’t constant—it actually accelerates as the generation progresses. The Parakeet paper [1] (which OP lifted their model architecture almost directly from [2]) gives a fairly robust treatment to the matter: > When we apply CFG to Parakeet sampling, quality is significantly improved. Ho…

    Comment linking /blog/2024/parakeet/

    on “Show HN: Dia, an open-weights TTS model for generating realistic dialogue”
  3. I have a sneaking suspicion it's because they lifted the model architecture almost directly from Parakeet: https://jordandarefsky.com/blog/2024/parakeet/ Parakeet references WhisperD which is at https://huggingface.co/jordand/whisper-d-v1a and doesn't include a full list of non-speech events that it's been trained with, except "(coughs)" and "(laughs)". Not saying the authors didn't do anything interesting here. The…

    Comment linking /blog/2024/parakeet/

    on “Show HN: Dia, an open-weights TTS model for generating realistic dialogue”

Search all of HN for jordandarefsky.com