---
title: "Yethikrishna R (@yethikrishnar) | Hashnode"
description: "Founder and lead engineer, Mynd Labs. Read the latest articles by Yethikrishna R on Hashnode."
url: "https://hashnode.com/@yethikrishnar"
---

@yethikrishnar

# Yethikrishna R

@yethikrishnar · Joined September 2026

Founder and lead engineer, Mynd Labs

[Website](https://founder.myndlabs.tech/)

### [Confiance d'une IA : ce que la moyenne peut cacher](https://yethikrishnar.hashnode.dev/confiance-d-une-ia-ce-que-la-moyenne-peut-cacher?utm_source=hashnode&utm_medium=feed)

Yethikrishna R examine une étude d'Umair Mehmood Imam sur Zuse, une famille de modèles qui choisissent parmi des réponses prédéfinies et attribuent une probabilité à chaque option. Le résultat le plus

3 min read · [yethikrishnar.hashnode.dev](https://yethikrishnar.hashnode.dev/confiance-d-une-ia-ce-que-la-moyenne-peut-cacher?utm_source=hashnode&utm_medium=feed)

[2h ago](https://hashnode.com/posts/confiance-d-une-ia-ce-que-la-moyenne-peut-cacher/6afce2e466e4dc78639f8c14)

### [How much speech data helps? Read the learning curve](https://yethikrishnar.hashnode.dev/how-much-speech-data-helps-read-the-learning-curve?utm_source=hashnode&utm_medium=feed)

Yethikrishna R examines research by Alvin Nahabwe and colleagues on a question that matters before a speech project spends more on transcription: how does recognition improve as the amount of training

3 min read · [yethikrishnar.hashnode.dev](https://yethikrishnar.hashnode.dev/how-much-speech-data-helps-read-the-learning-curve?utm_source=hashnode&utm_medium=feed)

[8h ago](https://hashnode.com/posts/how-much-speech-data-helps-read-the-learning-curve/6afc8e8347d31b106d4951a2)

### [Before the speech score: check what the benchmark repeats](https://yethikrishnar.hashnode.dev/before-the-speech-score-check-what-the-benchmark-repeats?utm_source=hashnode&utm_medium=feed)

Yethikrishna R examines a study by Christ Kekeli Keli, Steve Sanogo, Patrice Sebastiano, Hamad Aldenawi and Ryan Whetten on building a more comparable speech-recognition benchmark for Ewe. Their Nufo

3 min read · [yethikrishnar.hashnode.dev](https://yethikrishnar.hashnode.dev/before-the-speech-score-check-what-the-benchmark-repeats?utm_source=hashnode&utm_medium=feed)

[14h ago](https://hashnode.com/posts/before-the-speech-score-check-what-the-benchmark-repeats/6afc3a0d06e1fd94cb7f9676)

### [Kupima AI kwa Kiswahili: orodha ya lugha haitoshi](https://yethikrishnar.hashnode.dev/kupima-ai-kwa-kiswahili-orodha-ya-lugha-haitoshi?utm_source=hashnode&utm_medium=feed)

Yethikrishna R anachambua utafiti wa Manan Uppadhyay, Himanshu Beniwal, Prashant Kodali na Sunayana Sitaram kuhusu swali la msingi katika kupima AI: lugha ikitajwa katika jaribio, je, matumizi halisi

3 min read · [yethikrishnar.hashnode.dev](https://yethikrishnar.hashnode.dev/kupima-ai-kwa-kiswahili-orodha-ya-lugha-haitoshi?utm_source=hashnode&utm_medium=feed)

[20h ago](https://hashnode.com/posts/kupima-ai-kwa-kiswahili-orodha-ya-lugha-haitoshi/6afbe5b727cd1e69454ac02d)

### [Why an English confidence threshold needs a Swahili test](https://yethikrishnar.hashnode.dev/why-an-english-confidence-threshold-needs-a-swahili-test?utm_source=hashnode&utm_medium=feed)

Yethikrishna R examines research by Marek Šuppa and Jaroslav Kopčan on a practical problem for multilingual AI: a confidence rule tuned in English can behave differently when the application changes l

3 min read · [yethikrishnar.hashnode.dev](https://yethikrishnar.hashnode.dev/why-an-english-confidence-threshold-needs-a-swahili-test?utm_source=hashnode&utm_medium=feed)

[1d ago](https://hashnode.com/posts/why-an-english-confidence-threshold-needs-a-swahili-test/6afb914a98c8309909babf9b)
