Reference and routing skill for NVIDIA Nemotron 3.5 Transcribe. Use for model facts, checkpoint selection, inference constraints, and locating the canonical NeMo Speech main-stage training, fine-tuning, DFlash2, timestamp-serving, and quantization workflows; do not use as a substitute for those operational skills.
78%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./skills/nemotron-transcribe/SKILL.mdInvocation: /nemotron-transcribe.
Use this skill as the reference desk and workflow router for NVIDIA Nemotron 3.5 Transcribe. Keep NeMo Speech as the source of truth for executable speech training and export procedures.
INDEX.md to locate the smallest relevant source.context/quick-reference.md for fast routing.model-card.md for identity, variants, capabilities, and inference
boundaries.recipes/overview.md to select an available upstream workflow and see
which stages are still missing.usage-cookbook/Nemotron-3.5-Transcribe/README.md from the repository root.Resolve conflicts in this order:
Cite the stable report URL above only after it is publicly accessible.
Use the BF16 model card while planning fine-tuning and the destination precision's model card while planning deployment. The model cards define serving flags per precision; do not merge BF16, FP8, and NVFP4 launch settings into a single assumed profile.
| User intent | Canonical source |
|---|---|
| Construct a SALM from pretrained language and speech components | NeMo Speech train-speech-llm with salm_nemotron.yaml |
| Reproduce the exact released checkpoint | The main-stage template is parameterized; production component checkpoints, data blends, cluster values, and full validation evidence are not included |
| Fine-tune for a domain, language, or speech task | NeMo Speech finetune-speech-llm |
| Train or adapt a DFlash/DFlash2 draft | NeMo Speech train-dflash |
| Quantize a SALM checkpoint to FP8 or NVFP4 | NeMo Speech quantize-speech-llm |
| Serve BF16, FP8, or NVFP4 with vLLM | Nemotron Transcribe vLLM cookbook plus the selected model card |
| Request word timestamps and diarization metadata | Nemotron Transcribe vLLM cookbook, the selected model card, and the maintained NeMo Speech middleware; PR #16344 is change provenance |
| Reproduce RL post-training | No public Transcribe-specific recipe is linked yet; state the gap |
| Train the timestamp heads | No public training recipe is linked yet; do not substitute timestamp serving support |
| Reproduce published evaluation | No public automated harness, datasets, normalization, and scoring bundle is linked yet; state the gap |
When routing, give the relevant stage order and prerequisites first, then point to the upstream skill. Do not reproduce its detailed procedure locally.
Name the exact model ID and precision in every serving or evaluation answer. Do not imply that a quantized release is the preferred training source. When a user fine-tunes BF16 and then requests FP8 or NVFP4, route them to quantize their merged customized checkpoint. The published quantized releases are quantizations of NVIDIA's released BF16 model, not of the user's fine-tune.
Nemotron3_5TranscribeForConditionalGeneration; they require
a NeMo Speech revision that registers that architecture and its
Nemotron3_5TranscribeMTPModel draft. Old/old pairs may still work, but do
not mix pre-rename and post-rename components.main and an
unqualified model ID are moving dependencies.Do:
Do not:
NVIDIA-NeMo/Nemotron
a121b64
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.