Find your next open-source project

Search by name, purpose, or keyword — or paste a GitHub repository URL
All skills

digital-health-clinical-asr-build

Curate clinical terms, tag IPA pronunciations, and synthesize a NeMo manifest with audio.

  • Part of NVIDIA/skills
  • 1.9k installs
  • Machine Learning · Speech models

When to use it

You have a clinical specialty and a list of terms that ASR mistranscribes, but no benchmark audio or manifest yet.

For example

You say

Use digital-health-clinical-asr-build to build an oncology benchmark for chemo drug names like pembrolizumab and cisplatin, with clean and noisy audio.

You get
  • term_seed.csv
  • manifest.jsonl
  • audio wav clips

How it works

  • Terms pass through a three-tier IPA pipeline: verified overrides, then Merriam-Webster, then Magpie G2P, each tagged in the manifest.
  • A QA audition gate synthesizes one clip per term before the full voice, noise, and context product is generated.

Before installing

NVIDIA_API_KEY is required for hosted Magpie TTS, and Stage 1 (/digital-health-clinical-asr-setup) must be completed first.