Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/nemotron-asr-finetune
Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or language", it scopes the task, picks the cheapest sufficient path (word boosting → n-gram LM → fine-tuning), delegates each stage to the right sub-skill (data generation, training, evaluation, deployment), and answers cost/time/data questions along the way.
Passed 20 of 22 test cases with the skill, and 7 of 22 without it.
and 15 more in the full report
13 fixed7 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We completed 5 epochs of fine-tuning and generated multiple checkpoint files (`epoch_1.nemo` to `epoch_5.nemo`). We want to combine these checkpoints into a single final model before evaluation. Which stage and sub-skill handles this?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns checkpoint selection and averaging to the Research/Training stage using the nemo-speech-asr-finetune sub-skill | Missed | Passed |
The instructions your model reads when the skill loads.
Note: "Nemotron Speech" is the public-facing name for what NVIDIA documents today as Riva / Riva NIM; the acoustic models are trained and fine-tuned with NVIDIA NeMo. Commands, config paths, imports, and doc URLs still use "Riva" / "NeMo" — the rename is brand-only. Do not rename them.
This is a high-level orchestration skill, not a step-by-step training manual. Its job, given a goal such as "I want to fine-tune ASR for my domain/language", is to:
It owns the plan and the routing; the sub-skills own the execution. When a needed sub-skill does not exist yet, this skill names it as a placeholder and gives interim guidance.
Use for any request to make a Nemotron Speech / Riva ASR model work better on a specific domain or language — improving accuracy, reducing WER, adding a language, or planning a fine-tune. Start here even when the user names a specific technique, so the cheapest sufficient path is chosen and the right sub-skills are sequenced.
Run the loop below; each stage names the sub-skill it invokes. Full detail in references/workflow.md.
| # | Stage | What happens | Sub-skill |
|---|---|---|---|
| 1 | State the goal | Capture the target: domain/language, the errors, the metric. | Orchestration (this skill) |
| 2 | Clarify & scope | Ask the discovery questions: how much real audio? target eval set? latency/HW budget? deployment target? | Orchestration |
| 3 | Choose the path | Pick the cheapest sufficient rung (boosting → n-gram LM → fine-tune). Escalate only if quality is short; experiment while proposing the full plan. | Orchestration → Research/Training |
| 4 | Get the data right | If data is scarce/noisy: synthetic (TTS), TTS-friendly formatting, noise profiling/harvest, blend, score vendor samples; align customer data to training format; flag missing real data. | SDG / Data |
| 5 | Train | Apply the recipe (configs, hyperparameters, replay/curriculum, GPU/OOM preflight) and run. | Research / Training |
| 6 | Evaluate | Normalized WER on the domain set + A/B forgetting check on a general set; error-driven analysis to find the next lever. | Evaluation |
| 7 | Loop or ship | If short of target, loop to 4/5 with targeted data; else select/average checkpoints. Consult the user before more cycles. | Orchestration |
| 8 | Deploy | Export to NIM/HF, hot-swap the checkpoint, serve. | Deployment / Optimization |
Stages 4–8 are the fine-tune path (data → NeMo train → NeMo eval → Riva deploy). Cheaper rungs (boosting, custom vocab, n-gram LM) take a shorter branch owned by a single sub-skill — don't force them through the full loop. See the branch-by-rung table in references/workflow.md (§3b).
Throughout, answer the "along the way" questions (data volume, synthetic vs real, hours to reach a WER target, cost, GPU choice) — see references/planning-answers.md.
test cases passed, vs 7 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.