A 245M-parameter streaming English ASR model from Useful Sensors designed for low-latency, on-device transcription. Uses an 'ergodic' sliding-window encoder and achieves better WER than Whisper Large v3 on the OpenASR Leaderboard at a fraction of the size.
A strong 0.245B-parameter dense audio model from Useful Sensors. Treat the modality benchmarks above as the leading indicator of fit — composite scoring across modalities is still maturing.
Generated from this model’s benchmarks and ranking signals. Editor reviews refine it over time.
Access model weights, configuration files, and documentation.
See which devices can run this model and at what quality level.
On-device voice agents, live captioning, accessibility tools, voice command/interface systems, edge/embedded deployments where Whisper is too large or too slow.
View on Hugging Face