Series

ASR Fine-Tuning

Fine-tuning Whisper, Parakeet and other speech models on your own voice and languages, and measuring the result.

23 episodes
  1. 1

    Benchmarking Custom ASR Tools - Beyond The WER

    Benchmarking custom ASR fine-tunes: We're diving deep beyond the WER to truly measure performance.

    36:00 · 24 Nov 2025
  2. 2

    Building Custom ASR Tools

    Ever wondered how to build your own ASR tools from scratch? Discover the why and how in this episode!

    37:42 · 24 Nov 2025
  3. 3

    Building Your Own Whisper

    Ever wondered if you could build your own speech recognition tool? We dive deep into crafting custom ASR.

    34:41 · 24 Nov 2025
  4. 4

    Fine-Tuning ASR For Maximal Usability

    Fine-tuned ASR is just the start. Discover the next steps for deployment and maximizing usability.

    32:15 · 24 Nov 2025
  5. 5

    How To Fine Tune Whisper

    Build your own AI transcription tool! We'll walk you through fine-tuning Whisper, from data to notebook.

    31:42 · 24 Nov 2025
  6. 6

    If Your Voice Ages, Does Your Fine-Tune Become Useless?

    Your voice changes, but your fine-tuned model shouldn't become useless. We explore the biology of the larynx and ASR.

    38:26 · 24 Nov 2025
  7. 7

    AI Gets Personal: The Power of Voice Fine-Tuning

    AI that understands *your* voice? Dive into the fascinating world of fine-tuning and discover how AI gets personal.

    17:40 · 28 Nov 2025
  8. 8

    Fine-Tuning AI to Understand Your Voice

    Voice typing is changing everything. Join us as we explore the revolution of personalizing Whisper!

    23:27 · 5 Dec 2025
  9. 9

    Your AI, Evolving: Beyond the Static Snapshot

    Is your AI an "old suit" that no longer fits? We explore evolving AI that learns and adapts with you.

    25:43 · 7 Dec 2025
  10. 10

    Fine-Tuning Parakeet for Hebrew and Your Own Jargon

    NVIDIA's Parakeet beats Whisper on Android — but can you teach it Hebrew, or just your own jargon? Two answers, one much happier.

    22:52 · 23 Sept 2026
  11. 11

    Fine-Tuning Parakeet for Um-Free, Hebrish Speech

    Parakeet runs great on a phone — but fine-tuning it happens on a GPU. Here's the actual recipe for dropping ums and catching Hebrew.

    27:36 · 11 Oct 2026
  12. 12

    How Word Error Rate Lies to Us

    WER is the number everyone reports for speech recognition — and the one that agrees with human judgment least. Here's what it actually measures.

    26:49 · 14 Oct 2026
  13. 13

    How Much Voice Data Is Enough?

    Two hours of phone recordings took Hebrew code-switching from 20% to 60%. But when does more data stop mattering?

    20:14 · 16 Oct 2026
  14. 14

    Fine-Tuning for Code-Switched Hebrew on 2 Hours of Audio

    Two hours of one man's voice beat models trained on 120,000 hours — but only for code-switched Hebrew.

    22:25 · 16 Oct 2026
  15. 15

    Can You Snap Two Fine-Tunes Together Like LEGO?

    Two fine-tunes, one base model, and a question from Jerusalem: can you merge Hebrew code-switching with technical vocab — without retraining?

    35:31 · 16 Oct 2026
  16. 16

    How to Fine-Tune ASR on Noisy Audio

    A small noise library mixed into clean speech beats collecting hours of noisy recordings. Here's the ratio that actually works.

    42:22 · 17 Oct 2026
  17. 17

    When a Speech Model Can't Decide How to Write Dollars

    One dataset says "$20," another says "twenty dollars." Fine-tuning a speech model means finding out which convention wins — and why it matters.

    18:33 · 20 Oct 2026
  18. 18

    Where Do Tiny Speech Rules Live? A Ladder From Regex to LoRA

    A regex notebook, a WFST grammar, or a fine-tune? Where do tiny speech-rewrite rules actually belong in a 600M-parameter model?

    25:15 · 20 Oct 2026
  19. 19

    Where to Sit When You're Fine-Tuning Your Own Voice

    Your phone's built-in mic is the point — the setup around it is what ruins the takes. Rooms, remotes, and the app setting that deletes your data.

    21:46 · 20 Oct 2026
  20. 20

    Hebrish: Hebrew-Aware Dictation That Actually Works

    Two new speech models fix English-Hebrew code-switching dictation — and the whole training run cost about fifty cents of GPU time.

    22:01 · 21 Oct 2026
  21. 21

    What Actually Happens When You Train a Model

    Data in, model out — except the "data" is pairs, the split is the whole game, and one leaked speaker can fake your score.

    20:58 · 21 Oct 2026
  22. 22

    Two WERs, One Model: Inside ASR Eval Harnesses

    Same model, same audio, two different word error rates. The gap lives in the normaliser — and that's just layer two of three.

    22:35 · 22 Oct 2026
  23. 23

    Fine-Tuning ASR: When Your Model Memorizes You

    Your fine-tuned speech model aces your training recordings — but does it actually work on fresh audio?

    24:57 · 22 Oct 2026