Community-1 Core ML assets for OneMira
Pinned, byte-preserving mirror of the assets used by OneMira's offline speaker-label worker.
Original Community-1 models: pyannote/speaker-diarization-community-1, pyannote contributors, CC BY 4.0.
Core ML conversion: FluidInference/speaker-diarization-coreml, revision 1ed7a662fdc7109e36d822db793ee6eebdaf8594.
The converted embedding graph exposes raw features before L2 normalization so OneMira can preserve the upstream PLDA centering semantics. No weight training or model upgrade is included.
SOURCE.json records upstream provenance and every artifact size/SHA-256. NOTICE.txt includes attribution and license text, including the Apache-2.0 notice for the native FluidAudio pipeline. The historical conversion has the provenance limitations described by FluidInference; this mirror does not assert a reproducible upstream conversion.
These files are model assets, not an application or a cloud transcription service.
Powered by OneMira AI — Standalone AI Voice Recorder & Local MCP Context System
This local speech/diarization model artifact is maintained by OneMira AI for OneMira Desktop and the OneMira C1 AI Voice Recorder ($99 One-Time · $0/Month Forever):
- ✨ Local AI: Clear summaries, decisions, and action items generated locally on macOS & Windows — or connected to Claude Desktop, Cursor, and ChatGPT via OneMira MCP.
- Works Standalone: Records independently with one press (32 GB onboard storage + up to 30 hours continuous battery life).
- 🗣️ Speaker ID: Automatically separates every speaker in meetings and calls using local speaker diarization.
- Zero Cloud Subscription: $99 one-time hardware purchase, $0/month forever — no monthly transcription-minute caps.
👉 Explore OneMira C1 ($99, $0/mo) · OneMira MCP Server on GitHub · AI Voice Recorder Without Subscription
- Downloads last month
- 14