SKILLEMALL.ai
GitHub ↗ RU Sign in

CD nemo-speech-asr-finetune

Guide NeMo Speech users through ASR fine-tuning with container setup and Lhotse training.

NVIDIA-NeMo/Speech Agent Skills author: NVIDIA-NeMo Apache-2.0 8 files body ≈ 1 083 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Guide NeMo Speech users through ASR fine-tuning with container setup and Lhotse training.

As a process D 48/100 · Unfinished process — References files that are not bundled: examples/asr/speech_to_text_finetune.py, examples/asr/asr_ctc/speech_to_text_ctc_bpe.py, examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
83/100
safety, quality, tests
Safety 60%
100
Quality 40%
57
Run on models
none yet
Process rating
D
48/100
Unfinished process
References files that are not bundled: examples/asr/speech_to_text_finetune.py, examples/asr/asr_ctc/speech_to_text_ctc_bpe.py, examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: examples/asr/speech_to_text_finetune.py
  • warning missing-ref reference to a missing file: examples/asr/asr_ctc/speech_to_text_ctc_bpe.py
  • warning missing-ref reference to a missing file: examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py
  • warning missing-ref reference to a missing file: examples/asr/asr_hybrid_transducer_ctc/speech_to_text_hybrid_rnnt_ctc_bpe.py
  • warning missing-ref reference to a missing file: examples/asr/speech_multitask/speech_to_text_aed.py

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: examples/asr/speech_to_text_finetune.py, examples/asr/asr_ctc/speech_to_text_ctc_bpe.py, examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py
  • 0Tools and files. 5 referenced file(s) missing: examples/asr/speech_to_text_finetune.py, examples/asr/asr_ctc/speech_to_text_ctc_bpe.py, examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 1 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 100Steps. 35 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1083 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 89: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 35 items
  • +4Reference files are cited in the instructions (6 of 6)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.