Manual Model Loading

Overview

FluidAudio auto-downloads models from HuggingFace on first use. For offline or air-gapped environments, stage the CoreML bundles manually.

Per-Module Guides

Each module has specific assets and loading APIs:

ASR: Manual Model Loading — 4 CoreML bundles + vocabulary
Diarization: Getting Started — segmentation + embedding models
VAD: Getting Started — single Silero VAD bundle

General Pattern

Download assets via Git LFS, HuggingFace web UI, or copy from a machine that already ran the auto-downloader
Stage in a directory matching the expected layout
Call the load API with the staged directory URL

// Example: ASR
let models = try await AsrModels.load(
    from: URL(fileURLWithPath: "/opt/models/parakeet-tdt-0.6b-v3-coreml"),
    version: .v3
)

// Example: Diarization
let models = try await DiarizerModels.load(
    localSegmentationModel: segmentationURL,
    localEmbeddingModel: embeddingURL
)

// Example: VAD
let vadModel = try MLModel(contentsOf: modelURL, configuration: config)
let manager = VadManager(config: .default, vadModel: vadModel)

Cache Locations

Models are cached at ~/Library/Application Support/FluidAudio/Models/<repo> on macOS after first download.

Getting Started

Speech Recognition (ASR)

Speaker Diarization

Voice Activity Detection

Text-to-Speech (TTS)

Guides

Reference

Overview

Per-Module Guides

General Pattern

Cache Locations

​Overview

​Per-Module Guides

​General Pattern

​Cache Locations

Overview

Per-Module Guides

General Pattern

Cache Locations