Data & Analysis ✓ NVIDIA · Official clinical-asrspeech-evaluationkeyword-error-rateleaderboardnemo-manifestnvcfwer-cer-ser

Clinical ASR Evaluation and KER Leaderboard

Evaluate clinical ASR manifests and isolate terminology-recognition failures.

FollowSkills review · FSRS-2.0
Not recommended
55/ 100 5-point scale 2.8 / 5
Trust16 / 25 · 3.2/5

The skill explicitly discloses that every audio clip and reference transcript are sent to NVIDIA NVCF and prohibits real patient audio or PHI; it echoes the selected model and function ID, and documents local scoring, environment overrides, and a self-hosted path. Deductions apply because Bash/Write are declared, explicit user confirmation before the first external transmission is not required, rollback or deletion is not defined, and API-key handling and external-data isolation remain limited.

Reliability8 / 20 · 2.0/5

The main flow, manifest fields, metrics, artifacts, and several troubleshooting cases are specified, making the happy path plausible from static inspection. Deductions apply because execution depends on nvidia-riva-client, soundfile, and a working Riva/NVCF environment; RESOURCE_EXHAUSTED actually raises at the failing row while retry/resume is only advisory; no committed key-path test suite is shown; and some details depend on referenced material not supplied as executable tests. Static calibration limits this to 10 or less.

Adaptability9 / 15 · 3.0/5

The audience, trigger phrases, non-fit routes, manifest schema, and report outputs are relatively clear. Deductions apply because the default workflow is English/en-US and Latin-script oriented, Chinese and non-Latin support is limited, mainland-China reachability of grpc.nvcf.nvidia.com is not evidenced, and self-hosting requires additional deployment skills and prerequisites.

Convention10 / 15 · 3.3/5

The frontmatter, version 1.1.0, author, tags, stage links, license, references, examples, limitations, and troubleshooting provide a usable structure, with identifiable NVIDIA provenance and ownership. Deductions apply because there is no changelog, explicit maintenance commitment, or update path; the skill-card output description does not fully match the skill's Markdown/JSONL artifacts; and key recipe details remain chiefly in referenced files.

Effectiveness7 / 15 · 2.3/5

The skill gives a directly usable workflow for scoring a clinical ASR manifest, computing four metrics, producing a five-section leaderboard, and routing after evaluation; the core task is well defined. Deductions apply because static review cannot verify ASR calls, numerical correctness, or actual report usability, and execution still requires cloud access, dependencies, failed-row handling, and human review. Static calibration caps this at 7.

Verifiability5 / 10 · 2.5/5

Fixed function IDs, explicit algorithms, input/output schemas, representative splits, evaluation tasks, and an embedded benchmark report provide some auditability. Deductions apply because the benchmark is repository-authored evidence, with no independently verifiable CI, committed test suite covering key paths, or third-party reproduction; execution results therefore cannot be established statically. Static calibration caps this at 5.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 55f18499943e
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • Do not send real patient recordings, encounters, or PHI through this skill; despite the prohibition, require confirmation that inputs are synthetic or properly de-identified before execution.
  • The default path depends on external NVIDIA NVCF; verify mainland-China reachability, organizational compliance, and cost controls first. Mid-batch RESOURCE_EXHAUSTED failures lack a reliable built-in resume mechanism.
  • The workflow is primarily for English clinical ASR; Chinese and other-language normalization, tokenization, and KER semantics lack supporting evidence.
  • The repository benchmark is not a substitute for independent execution; publication should add tests covering ASR calls, scoring, and failure paths.
Review evidence [1][2][3][4][5][6][7][8][9]
See the full review method →

What does this skill do, and when should you use it?

This skill is Stage 3 of NVIDIA’s Clinical ASR Flywheel and accepts a NeMo-format manifest with clinical extension fields. It transcribes each referenced audio file through an NVIDIA NVCF ASR NIM, then computes WER, CER, KER, and SER locally. It produces a five-section KER leaderboard and routes the workflow toward fine-tuning, benchmark rebuilding, or stronger evaluation based on priority-category KER and ipa_source splits. It is intended for synthetic clinical speech, not real patient recordings or PHI.

Reads manifest.jsonl together with audio_filepath, text, term, entity_category, ipa_source, voice_id, noise_level, and context_type; calls the default NVIDIA NVCF nvidia/parakeet-tdt-0.6b-v2 offline gRPC ASR NIM, with environment-variable overrides for the model or endpoint; writes per_sample.json containing ref, hyp, and preserved clinical metadata; computes WER, CER, strict contiguous-match KER, and SER under the defined normalization; and produces a five-section leaderboard covering headline metrics, entity_category, ipa_source, noise_level, and worst-first per-term KER.

  1. A clinical ASR researcher has a 100-plus-row NeMo manifest with term labels and needs a Parakeet baseline evaluation.
  2. A healthcare speech team wants to measure the effect of merriam-webster versus magpie_g2p pronunciation sources on term recognition.
  3. An evaluation engineer needs KER breakdowns by drug, procedure, anatomy, or other entity categories instead of relying on overall WER.
  4. A model team needs evidence for whether to expand terminology and pronunciation data or proceed to fine-tuning.

What are this skill's strengths and limitations?

Pros
  • Reports WER, CER, KER, and SER while making clinical terminology recognition the headline signal.
  • Requires an ipa_source breakdown that can expose pronunciation-hint coverage gaps.
  • Provides an explicit decision tree connecting evaluation results to rebuilding, fine-tuning, or harder evaluation.
  • Includes pure-Python scoring recipes, so jiwer is optional.
Limitations
  • Defaults to English and en-US Latin-script normalization assumptions.
  • Strict contiguous KER treats near-misses such as cefa zolin as failures.
  • Each evaluation run uses one model; model comparisons require separate runs and result diffs.
  • The ASR stage sends each audio file and reference transcript to NVIDIA NVCF and must not be used with real patient audio or PHI.
  • Requires NVIDIA_API_KEY, nvidia-riva-client, soundfile, available audio files, and external network access.

How do you install this skill?

Install the specific skill with the NVIDIA skills CLI:

npx skills add nvidia/skills --skill digital-health-clinical-asr-eval --yes

The README does not document a separate client-specific installation path for this skill. After installation, the skill is available when the agent loads it for a relevant task.

How do you use this skill?

Provide a NeMo-format manifest.jsonl with the clinical extension fields and existing audio files, then export NVIDIA_API_KEY. Example trigger: "Score my ASR manifest at manifest.jsonl and generate the five-section KER leaderboard." Before transcription, confirm the selected NIM and resolved function-id; each audio file and reference transcript is sent to an external NVIDIA service, so use synthetic Stage 2 audio. If no manifest exists, use digital-health-clinical-asr-build first. Authentication, protocol, and model-catalog questions are outside this skill’s scope.

How does this skill compare with similar options?

Compared with digital-health-clinical-asr-build, this skill evaluates an existing manifest rather than generating audio or building the benchmark. Compared with digital-health-clinical-asr-finetune, it scores KER first and determines whether fine-tuning is justified. ASR model catalogs, authentication, gRPC protocol, and self-hosted NIM configuration are routed to riva-asr or the related skills.

FAQ

Can it be used with real patient recordings?
No. The source explicitly requires synthetic audio and prohibits passing real ASR recordings, real patient encounters, or PHI through this skill.
Will an evaluation consume external-service credits?
It may consume NVIDIA API credits because every manifest audio file is sent to NVIDIA NVCF; the source does not provide pricing.
What should I do when KER is high but WER is low?
Inspect the ipa_source split first. If merriam-webster rows perform well while magpie_g2p rows perform poorly, return to Step 2d of digital-health-clinical-asr-build rather than fine-tuning first.
Can I use the skill without a manifest?
No. First create or obtain a NeMo manifest with the required clinical extension fields through digital-health-clinical-asr-build.

More skills from this repository

All from NVIDIA/skills

Dev & Engineering ✓ NVIDIA · Official

Clinical ASR Flywheel: Environment Setup

Validate that a clinical ASR evaluation environment can complete a TTS-to-ASR round trip through NVIDIA-hosted speech services.

Data & Analysis ✓ NVIDIA · Official

Clinical ASR Fine-Tuning

Fine-tune Parakeet TDT v2 with NeMo for clinical vocabulary and close the loop with offline KER evaluation.

Data & Analysis ✓ NVIDIA · Official

Clinical ASR Benchmark Builder

Build pronunciation-aware NeMo evaluation benchmarks for clinical speech recognition.

Data & Analysis ✓ NVIDIA · Official

Nemotron Speech ASR Customization Orchestrator

Chooses and coordinates the lowest-cost path for adapting speech recognition to a domain or language.

Dev & Engineering ✓ NVIDIA · Official

NeMo Evaluator Plugin Skill

Run and manage NeMo Platform model evaluations through the Evaluator CLI and Python SDK.

Automation & Ops ✓ NVIDIA · Official

Nemotron Speech NIM Skill

Guides deployment and operation of NVIDIA Riva ASR, TTS, and translation NIMs.

Data & Analysis ✓ NVIDIA · Official

NeMo Data Designer Synthetic Data Skill

Build synthetic datasets and declarative data-generation pipelines from a natural-language description.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Installation Guide

Choose and verify the right NeMo Relay path for CLIs, language packages, and maintained frameworks.

Data & Analysis ✓ NVIDIA · Official

Nemotron Retrieval Recipes

Plan, debug, tune, evaluate, export, and deploy Nemotron embedding and reranking recipes.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Quick Start

Helps first-time NeMo Relay users prove observable execution value through the smallest suitable trial.

Dev & Engineering ✓ NVIDIA · Official

NeMo AutoModel Model Onboarding

A structured guide for adding new LLM, MoE, and VLM architectures to NeMo AutoModel.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Plugin Builder

Guides reusable NeMo Relay runtime behavior into configurable plugins.

Automation & Ops ✓ NVIDIA · Official

NeMo Relay Observability Plugin

Configure NeMo Relay event capture and telemetry exports.

Dev & Engineering ✓ NVIDIA · Official

Jetson BSP Source Builder

Rebuild Jetson BSP device trees, kernels, and modules from source changes and produce a deployable artifact manifest.

Dev & Engineering ✓ NVIDIA · Official

NeMo AutoModel Distributed Training

Choose and configure multi-GPU and multi-node training strategies for NeMo AutoModel.

Writing & Content ✓ NVIDIA · Official

NeMo-RL Documentation Conventions

Keeps NeMo-RL documentation, indexes, and docstrings consistent.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Migration Assistant

Safely migrate NeMo Flow projects to NeMo Relay.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Adaptive Tuning

Tune NeMo Relay plugin behavior from runtime signals with measured, reversible rollouts.

Data & Analysis ✓ NVIDIA · Official

Nemotron Customization Pipelines

Plan, configure, and chain existing Nemotron steps for data preparation, training, alignment, conversion, optimization, and evaluation.

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Runtime Integration Debugger

Diagnose application-side runtime failures after NeMo Relay is installed or imported.

Related skills