omi-med-stt 0.1.19

CLI for Omi Med STT v1 medical speech-to-text

Omi Med STT Runtime

Command-line runtime for Omi Med STT v1, an English medical speech-to-text model built from NVIDIA Parakeet TDT 0.6B v2.

The package downloads the right model artifact for your machine and transcribes audio locally.

Install

pip install -U omi-med-stt

Apple Silicon:

pip install -U "omi-med-stt[mlx]"

NVIDIA CUDA / NeMo:

pip install -U "omi-med-stt[nemo]"

Run

omi-med-stt audio.wav

Useful options:

omi-med-stt audio.wav --json
omi-med-stt audio.wav --runtime mlx
omi-med-stt audio.wav --runtime nemo
omi-med-stt audio.wav --runtime cpp
omi-med-stt check

Runtime Choices

Platform	Default runtime	Model artifact
Apple Silicon	mlx	omi-health/omi-med-stt-v1-mlx-q8
NVIDIA CUDA	nemo	omi-health/omi-med-stt-v1
Linux/Windows CPU	cpp	omi-health/omi-med-stt-v1-gguf

The canonical model is the NeMo checkpoint. MLX and GGUF are runtime exports.

CPU setup:

omi-med-stt install-cpp --cpp-backend cpu
omi-med-stt audio.wav --runtime cpp

The CPU path uses a patched parakeet.cpp runtime and downloads the q8_0 GGUF artifact only. It does not download the NeMo or MLX weights.

Evaluation Snapshot

Private benchmark: OmiMedSTT-Private-v1, 1,513 rows / 7.18 hours of held-out medical audio.

Model	WER	M-WER	Drug M-WER	Medical Recall
Omi Med STT v1 NeMo	8.30%	2.37%	4.75%	97.95%
Parakeet TDT 0.6B v2 base	16.45%	8.36%	8.60%	96.20%
Qwen3 ASR 1.7B	10.72%	3.13%	6.11%	97.21%
VibeVoice-ASR 9B	11.10%	1.78%	1.36%	98.71%

Runtime artifacts differ slightly:

Artifact	WER	M-WER	Drug M-WER	Medical Recall
NeMo canonical	8.30%	2.37%	4.75%	97.95%
MLX full precision	8.59%	2.65%	5.20%	97.70%
MLX q8	8.61%	2.75%	5.20%	97.63%
GGUF q8_0	9.12%	3.20%	6.33%	97.53%

High-level evaluation summary: docs/evaluation-summary.md.

Model Repositories

• Canonical NeMo: omi-health/omi-med-stt-v1
• Apple Silicon q8: omi-health/omi-med-stt-v1-mlx-q8
• Apple Silicon full precision: omi-health/omi-med-stt-v1-mlx
• Linux/Windows CPU GGUF: omi-health/omi-med-stt-v1-gguf

If the model repositories are private before launch, authenticate first:

huggingface-cli login

CUDA Note

If --runtime nemo fails with a CUDA driver mismatch, install a PyTorch wheel matching your driver before installing the NeMo extra. For example, on CUDA 12.8 hosts:

pip install torch --index-url https://download.pytorch.org/whl/cu128
pip install -U "omi-med-stt[nemo]"

Development

git clone https://github.com/Omi-Health/omi-med-stt-runtime
cd omi-med-stt-runtime
pip install -e ".[dev]"
python scripts/prepublish_check.py --skip-build
python -m pytest -q tests

Safety

Omi Med STT v1 is speech-to-text only. It is not a diagnostic, triage, prescribing, or clinical decision model, and it is not clinically validated. Transcripts must be reviewed before any clinical use.

License And Attribution

Runtime code is MIT licensed.

Model weights are CC-BY-4.0 and are derived from nvidia/parakeet-tdt-0.6b-v2. Omi Med STT v1 is not an NVIDIA model.

The CPU runtime uses parakeet.cpp.