All skills
digital-health-clinical-asr-setup
Verify your NVIDIA_API_KEY works by round-tripping a clinical sentence through Magpie TTS and Parakeet ASR.
- Part of NVIDIA/skills
- 1.9k installs
- Machine Learning · Speech models
When to use it
You have an NVIDIA_API_KEY and a fresh Python environment but haven't confirmed the hosted speech stack actually responds.
For example
You say
Set up the Clinical ASR Flywheel for me — I have my NVIDIA_API_KEY exported and want to confirm the hosted TTS and ASR stack works before I start curating terms.
You get
- Length-only key check
- Installed Python dependencies
- TTS-to-ASR smoke-test transcript
How it works
- Shows a data-disclosure table naming NVIDIA NVCF and Merriam-Webster as the two external endpoints before any text or audio is sent.
- The smoke test must actually run, not be deferred, since it gates whether later stages can reach the hosted stack.
- Merriam-Webster lookup is optional; without it, Stage 2 falls back to Magpie G2P with weaker coverage on rare clinical terms.
Before installing
An NVIDIA_API_KEY from build.nvidia.com is required for the hosted Magpie TTS and Parakeet/Nemotron ASR calls; Python 3.10+ is also needed.
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.