VAD Getting Started

import FluidAudio

let manager = try await VadManager(
    config: VadConfig(defaultThreshold: 0.75)
)

let samples = try AudioConverter().resampleAudioFile(
    URL(fileURLWithPath: "audio.wav")
)

var segmentation = VadSegmentationConfig.default
segmentation.minSpeechDuration = 0.25
segmentation.minSilenceDuration = 0.4
segmentation.speechPadding = 0.12

let segments = try await manager.segmentSpeech(samples, config: segmentation)
for (index, segment) in segments.enumerated() {
    print(String(format: "Segment %02d: %.2f-%.2fs", index + 1, segment.startTime, segment.endTime))
}

let clips = try await manager.segmentSpeechAudio(samples, config: segmentation)
print("Extracted \(clips.count) buffered segments ready for ASR")

let results = try await manager.process(samples)
for (index, chunk) in results.enumerated() {
    print(String(format: "Chunk %02d: prob=%.3f", index, chunk.probability))
}

let modelURL = URL(
    fileURLWithPath: "/opt/models/silero-vad-coreml/silero-vad-unified-256ms-v6.0.0.mlmodelc",
    isDirectory: true
)
var configuration = MLModelConfiguration()
configuration.computeUnits = .cpuOnly
let vadModel = try MLModel(contentsOf: modelURL, configuration: configuration)
let manager = VadManager(config: .default, vadModel: vadModel)

# Offline segmentation
swift run fluidaudio vad-analyze audio.wav

# Streaming mode
swift run fluidaudio vad-analyze audio.wav --streaming --min-silence-ms 300

# Both modes
swift run fluidaudio vad-analyze audio.wav --mode both

# Benchmark
swift run fluidaudio vad-benchmark --num-files 50 --threshold 0.3