<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v" -->

---
title: Evaluate Clinical ASR Models Faster with Agent Skills...
description: Clinical ASR systems struggle with rare medical terminology like drug names and procedure terms. This post presents a repeatable evaluation flywheel using...
canonical: https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech | daily.dev
og:description: Clinical ASR systems struggle with rare medical terminology like drug names and procedure terms. This post presents a repeatable evaluation flywheel using...
og:url: https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v
og:image: https://api.daily.dev/og/posts/ZRLoBjd2v.png
og:image:alt: Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech

**[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 12 min read · 1 upvotes · 0 comments

## Summary

Clinical ASR systems struggle with rare medical terminology like drug names and procedure terms. This post presents a repeatable evaluation flywheel using NVIDIA agent skills, NeMo Data Designer, and Nemotron Speech to generate pronunciation-aware synthetic clinical audio without requiring real patient recordings. The workflow guides developers through defining a clinical profile, expanding seed terms into SSML-annotated sentences with IPA phoneme markup, synthesizing audio via Magpie TTS, and evaluating ASR quality using WER, CER, KER, and SER metrics. A manual pronunciation review loop handles terms missing from dictionaries. The flywheel routes developers to the right next step — more data, pronunciation fixes, or model fine-tuning — based on entity-level error patterns rather than aggregate scores alone. Limitations include the small benchmark size and the need for real-world audio for production validation.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://developer.nvidia.com/blog/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech>

## Similar posts on daily.dev

- [How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent](https://daily.dev/posts/how-to-fine-tune-nemotron-3-5-asr-for-your-language-domain-or-accent-lmayxxp44) · Hugging Face · 0 upvotes · 0 comments
- [Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR](https://daily.dev/posts/scaling-real-time-voice-agents-with-cache-aware-streaming-asr-v2urtcsgr) · Hugging Face · 15 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#healthcare](https://daily.dev/tags/healthcare), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#nvidia-nemo](https://daily.dev/tags/nvidia-nemo)

[View this post on daily.dev](https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech","url":"https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v"},"datePublished":"2026-06-09T15:02:15.723Z","dateModified":"2026-06-09T16:20:13.833Z","description":"Clinical ASR systems struggle with rare medical terminology like drug names and procedure terms. This post presents a repeatable evaluation flywheel using...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a29385bb84c2b06e0d777bf5a18bcde0?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/a29385bb84c2b06e0d777bf5a18bcde0?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/evaluate-clinical-asr-models-faster-with-agent-skills-and-nvidia-nemotron-speech-zrlobjd2v","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,healthcare,speech-recognition,nvidia-nemo","timeRequired":"PT12M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Evaluate Clinical ASR Models Faster with Agent Skills and NVIDIA Nemotron Speech"}]}
```

