coremlit 0.1.0

Safe, synchronous CoreML runtime for macOS (CPU/GPU/Neural Engine) with opt-in on-device multimodal pipelines: speech (Whisper STT, forced alignment, speaker diarization, Silero VAD), AudioSet sound-event tagging, and audio/text/image embeddings (CLAP, granite, SigLIP)

coremlit

There is currently very little information to present on this page because Docs.rs has only limited support for extracting structured feature metadata from Cargo crates. This issue is tracked in Rust RFC #3416. Check this library's main docs, readme, and Cargo.toml in case its authors have documentation for features available there instead.

This version has 16 feature flags, 0 of them enabled by default.

default

This feature flag does not enable additional features.

align

align-oracle

ced

clap

commercial-face-arcface

face

granite

identity

lid

nl-recognizer

serde

siglip

speaker

tracing

vad

whisper