Diarization Getting Started

import FluidAudio

let models = try await DiarizerModels.downloadIfNeeded()
let diarizer = DiarizerManager()
diarizer.initialize(models: models)

let samples = try AudioConverter().resampleAudioFile(
    URL(fileURLWithPath: "meeting.wav")
)
let result = try diarizer.performCompleteDiarization(samples)

for segment in result.segments {
    print("Speaker \(segment.speakerId): \(segment.startTimeSeconds)s - \(segment.endTimeSeconds)s")
}

let config = DiarizerConfig(
    clusteringThreshold: 0.7,      // Speaker separation (0.0-1.0)
    minSpeechDuration: 1.0,         // Minimum segment duration (seconds)
    minSilenceGap: 0.5,             // Minimum silence between speakers
    minActiveFramesCount: 10.0,     // Minimum active frames
    debugMode: false
)
let diarizer = DiarizerManager(config: config)

let aliceAudio = loadAudioFile("alice_sample.wav")
let aliceEmbedding = try diarizer.extractEmbedding(aliceAudio)

let alice = Speaker(id: "Alice", name: "Alice", currentEmbedding: aliceEmbedding)
let bob = Speaker(id: "Bob", name: "Bob", currentEmbedding: bobEmbedding)
diarizer.speakerManager.initializeKnownSpeakers([alice, bob])

// Will use "Alice" instead of "Speaker_1" when matched
let result = try diarizer.performCompleteDiarization(audioSamples)

let basePath = "/opt/models/speaker-diarization-coreml"
let segmentation = URL(fileURLWithPath: basePath)
    .appendingPathComponent("pyannote_segmentation.mlmodelc")
let embedding = URL(fileURLWithPath: basePath)
    .appendingPathComponent("wespeaker_v2.mlmodelc")

let models = try await DiarizerModels.load(
    localSegmentationModel: segmentation,
    localEmbeddingModel: embedding
)

swift run fluidaudio process meeting.wav --output results.json --threshold 0.6
swift run fluidaudio diarization-benchmark --auto-download