All skills
digital-health-clinical-asr-finetune
Fine-tune Parakeet TDT v2 with stock NeMo SFT and re-evaluate KER offline.
- Part of NVIDIA/skills
- 1.9k installs
- Machine Learning · Speech models
When to use it
You already have a scored baseline manifest with priority-category KER above 0.3 and need to know whether fine-tuning actually lowers it.
For example
You say
Use digital-health-clinical-asr-finetune on my 130-row clinical manifest; drug-name KER is 0.42 and I want to see if SFT brings it down.
You get
- adapted_model.nemo
- leaderboard_cycle2.md
- KER delta decision
How it works
- Splits the manifest row-disjoint and stratified by entity_category, defaulting to 20% validation.
- Uses the stock speech_to_text_finetune.py script with bf16-mixed precision for TDT stability.
- Warns against fine-tuning nemotron-speech-streaming-en-0.6b because its SFT path collapses.
Before installing
Needs a CUDA host (16 GB VRAM minimum), the NeMo container nvcr.io/nvidia/nemo:25.11.01, and the finetune-asr and riva-asr-custom skills installed alongside; NVIDIA_API_KEY is required for the offline cycle N+1 eval and any NIM deploy.
Also in this pack
- accelerated-computing-cudf3.2kGuides GPU DataFrame work with cuDF, including pandas acceleration, joins, groupby, file I/O and multi-GPU jobs.
- cuopt-developer2.8kModifies, builds, tests, and debugs NVIDIA cuOpt source code and prepares contributions.
- cuopt-install2.6kInstalls cuOpt for Python, C, or server via pip, conda, or Docker and verifies it works.
- data-designer2.6kGenerates a synthetic dataset from your description of the data you need.