Data & Analysis ✓ NVIDIA · Official speech-to-textasr-fine-tuningdomain-adaptationword-boostinglanguage-modelwer-evaluationnvidia-rivanvidia-nemo

Nemotron Speech ASR Customization Orchestrator

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

FollowSkills review · FSRS-2.0
Not recommended
56/ 100 5-point scale 2.8 / 5
Trust17 / 25 · 3.4/5

The skill requires scoping first, baseline measurement, least-cost path selection, and user consultation before additional tuning cycles; it also distinguishes offline evaluation from served evaluation, reducing operational confusion. Points are deducted because handling of sensitive speech/customer data, least-privilege permissions, dependency security, rollback, and explicit pre-deployment confirmation are not specified.

Reliability8 / 20 · 2.0/5

The workflow, path ladder, sub-skill ownership, and placeholder fallback guidance are broadly self-consistent, and missing sub-skills are to be disclosed rather than silently assumed. Points are deducted because this review is static and does not reproduce key paths; detailed version compatibility, command failures, and abnormal-input diagnostics are largely delegated to external sub-skills.

Adaptability11 / 15 · 3.7/5

Triggers, audience scenarios, input questions, path branches, and non-fit cases are relatively clear, including exclusions for pure deployment, OpenAI Whisper, and text-LLM fine-tuning. Points are deducted because Chinese-language support and mainland-China network reachability are not addressed, and the core workflow depends on multiple external NVIDIA/Riva/NeMo components.

Convention10 / 15 · 3.3/5

The documentation is layered and includes workflow, path selection, sub-skill registry, planning answers, limitations, version 1.0.0, Apache-2.0 licensing, and repository update guidance. Points are deducted for missing recommended Instructions and Examples sections, nonconforming author metadata, and incomplete skill-level changelog, maintainer, and troubleshooting details.

Effectiveness6 / 15 · 2.0/5

The skill provides useful high-level ASR adaptation planning, cost-aware routing, delegation, and evaluation criteria; the committed benchmark report indicates positive evaluation results, though it is only source-file evidence here. Points are deducted because the skill does not itself execute training, evaluation, or deployment, final utility depends on other skills, and no independent direct-output verification was performed.

Verifiability4 / 10 · 2.0/5

A revision-pinned source, cited primary documentation, evaluation guidance, evals.json, and an NVSkills-Eval report provide some auditability. Points are deducted because independently reproducible execution logs, raw evaluation artifacts, and corroboration from multiple evidence types are absent, so a higher static evidence score is not justified.

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 treat this orchestration skill as a training or deployment executor; confirm required sub-skills, versions, and external-service availability first.
  • Before processing customer audio, transcripts, or synthetic data, establish privacy, access-control, retention, and data-transfer requirements.
  • Before deployment or expensive training, obtain confirmation of budget, hardware, model versions, rollback, and the current Riva/NeMo support matrix.
  • For mainland-China users, separately verify reachability of NVIDIA documentation, images, models, and service endpoints.
See the full review method →

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

This skill orchestrates domain and language adaptation for NVIDIA Nemotron Speech (Riva) / NeMo ASR. It scopes audio data, evaluation, target metrics, latency, and hardware before choosing among word boosting, n-gram language modeling, and fine-tuning. It owns planning, routing, and answers about cost, time, and data, while dedicated sub-skills handle training, evaluation, and deployment. It fits teams trying to reduce WER, correct jargon errors, handle noise, or add a language, but it is not a step-by-step training manual.

Collects the target domain or language, error patterns, evaluation metric, real-audio volume, deployment target, and latency or hardware budget; selects word boosting, custom vocabulary/pronunciation, n-gram LM, fine-tuning, or cross-language transfer; routes data generation, training, evaluation, and deployment to named sub-skills; plans blends of real and synthetic data; requires normalized domain-set WER plus a general-set forgetting check; loops for targeted improvements or proceeds to Riva/NIM deployment; and answers questions about data volume, GPUs, time, and cost.

  1. A call-center team sees industry jargon misrecognized in noisy calls and needs to decide whether boosting, a language model, or fine-tuning is appropriate.
  2. A speech product team wants to adapt Riva ASR to a new language and needs to assess checkpoints, data requirements, and cross-language transfer.
  3. An enterprise has domain text but little labeled audio and wants to pilot an n-gram LM for domain phrasing before investing in acoustic fine-tuning.
  4. An ASR engineering team has transcribed target-domain audio and needs a plan covering NeMo fine-tuning, WER evaluation, forgetting checks, and deployment.

What are this skill's strengths and limitations?

Pros
  • Uses a cost-ordered ladder from word boosting and language modeling to fine-tuning.
  • Covers data planning, training, evaluation, forgetting checks, and deployment routing.
  • Requires domain WER and a general-set A/B check instead of relying only on training logs.
  • Addresses scarce real data, synthetic data, noise, GPU choice, time, and cost questions.
Limitations
  • Orchestration only; it does not provide the complete training or deployment execution itself.
  • Some required sub-skills may be placeholders and then provide only interim guidance.
  • Training paths require a GPU, and NeMo/Riva commands, configurations, and model support can change by release.
  • The supplied sources provide no skill-specific test results, concrete pricing, or guaranteed WER improvement.

How do you install this skill?

Install the individual skill from NVIDIA’s collection with the skills CLI:

npx skills add nvidia/skills --skill nemotron-asr-finetune --yes

The README does not document a client-specific destination; the CLI prompts for the installation target.

How do you use this skill?

After installation, give the agent a concrete ASR customization request, such as: "Fine-tune ASR for my noisy call-center domain and reduce WER." The agent should first ask about real-audio volume, the target evaluation set, latency/hardware budget, and deployment target, then select the cheapest sufficient path. Available sub-skills perform the detailed training, evaluation, and deployment work; missing sub-skills are identified as placeholders.

How does this skill compare with similar options?

The skill explicitly chooses among word boosting, custom vocabulary/pronunciation, n-gram LM, fine-tuning, and finally training from scratch or cross-language transfer. These are staged ASR customization paths rather than competing products.

FAQ

Does it perform the ASR fine-tuning itself?
No. It scopes the problem, selects the path, and orchestrates stages; execution is delegated to sub-skills such as nemo-speech-asr-finetune.
What if I have very little labeled audio?
It first evaluates cheaper options such as word boosting or n-gram LM and can plan synthetic data to fill measured gaps, while treating real target-domain audio as the usual bottleneck.
How much data is needed for fine-tuning?
It answers this in context. Its path summary cites the NIM guide’s 100+ hour recommendation and describes roughly 10 hours as a floor only when mixed to reduce catastrophic forgetting.
Is it useful if I only want to deploy an existing Riva model?
Only to a limited extent. Deployment is handled by the nemotron-speech sub-skill; this skill focuses on customization planning and orchestration.

More skills from this repository

All from NVIDIA/skills

Automation & Ops ✓ NVIDIA · Official

Nemotron Speech NIM Skill

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

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 Evaluation and KER Leaderboard

Evaluate clinical ASR manifests and isolate terminology-recognition failures.

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

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

Nemotron Retrieval Recipes

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

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 MBridge Recipe Recommender

Recommends adjustable Megatron Bridge recipes for your model, GPU budget, and training goal.

Data & Analysis ✓ NVIDIA · Official

Cosmos-Embed Video Retrieval & Fine-Tuning

Use Cosmos-Embed1 to embed, retrieve, deduplicate, and fine-tune video-text data.

Data & Analysis ✓ NVIDIA · Official

Clinical ASR Benchmark Builder

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

Data & Analysis ✓ NVIDIA · Official

NV Brain MRI Diffusion Fine-Tuner

Fine-tune the NV-Generate-CTMR diffusion UNet from NIfTI brain MRI training volumes.

Data & Analysis ✓ NVIDIA · Official

Hugging Face GPU Fine-Tuning

Build reproducible Hugging Face fine-tuning pipelines on local NVIDIA GPUs.

Automation & Ops ✓ NVIDIA · Official

Isaac for Healthcare E2E Workflow

Run the Isaac for Healthcare pipeline from recording through validation.

Data & Analysis ✓ NVIDIA · Official

TAO ChangeNet Root Cause Analyzer

Uses image evidence to identify why NVIDIA TAO Visual ChangeNet classification experiments fail.

Dev & Engineering ✓ NVIDIA · Official

NeMo Evaluator Plugin Skill

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

Dev & Engineering ✓ NVIDIA · Official

NeMo Relay Adaptive Tuning

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

Automation & Ops ✓ NVIDIA · Official

RAG Performance Benchmark

Benchmark a deployed NVIDIA RAG Blueprint server and expose latency, throughput, and bottleneck behavior from one YAML config.

Data & Analysis ✓ NVIDIA · Official

TAO CLIP Fine-Tuning and Deployment

Train and deploy NVIDIA TAO CLIP for image-text retrieval, zero-shot classification, and embedding extraction.

Data & Analysis ✓ NVIDIA · Official

TAO AutoML Tuning

Run governed hyperparameter optimization for NVIDIA TAO networks across supported SDK platforms.

Dev & Engineering ✓ NVIDIA · Official

TAO Sparse4D Training Skill

Guides agents through training, evaluation, export, quantization, and inference for multi-camera temporal 3D detection and tracking.

Related skills