Iris uses direct finite command recognition, our Hey Iris wake model, Silero VAD and a session-only speaker reference for one command. Recognition runs locally without ASR/STT transcription or a language model. Designed voices are synthetic and do not establish independent human, household or Raspberry Pi acceptance. Pinned data/source/license receipts, quantitative results and limitations follow. The preserved historical card records earlier experiments and source terms. The release uses immutable original recordings and explicitly labelled generated or constructed examples. reproduction-inputs.json is the machine-readable index of pinned files, source revisions, SHA-256 values, audio…
Independent publisher
Justin Jose Ruaya
justinruaya123
Models in Library0
Datasets in Library1
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.