Smart Turn — 话轮结束检测

import SpeechVAD

let turn = try await SmartTurnModel.fromPretrained()
try turn.prewarm()   // compile the graph before the first real pause

let probability = try turn.turnCompleteProbability(
    audio: utterance, sampleRate: 16_000)
if probability >= SmartTurnModel.defaultThreshold {
    // finished turn — reply now
}

let vad = try await SileroVADModel.fromPretrained(engine: .coreml)
let turn = try await SmartTurnModel.fromPretrained()

let processor = StreamingVADProcessor(
    model: vad,
    config: .sileroDefault,
    turnCompletion: turn,
    turnCompletionConfig: TurnCompletionConfig(threshold: 0.5, maxSilenceDuration: 2.0))

for chunk in microphoneChunks {            // Float32 @ 16 kHz
    for event in processor.process(samples: chunk) {
        switch event {
        case .speechStarted(let time): print("speech at \(time)s")
        case .speechEnded(let segment): print("turn \(segment.startTime)–\(segment.endTime)s")
        }
    }
}
let remaining = processor.flush()

import SpeechCore
import SpeechVAD

let smartTurn = try await SmartTurnModel.fromPretrained()
try smartTurn.prewarm()

var config = PipelineConfig()
config.turnCompletionThreshold = 0.5   // pause ends the turn when p >= this
config.turnCompletionMaxSilence = 2.0  // seconds of silence that end a held turn anyway; 0 = never

let pipeline = VoicePipeline(stt: stt, tts: tts, vad: vad, config: config, onEvent: { print($0) })
pipeline.setTurnCompletion(smartTurn)   // before start(); nil detaches
pipeline.start()

# Probability, complete/incomplete verdict and inference time for one utterance
speech turn utterance.wav

# Custom threshold, JSON output
speech turn utterance.wav --threshold 0.7 --json

# Local bundle, no download
speech turn utterance.wav --model-dir ~/smart-turn-coreml

# Streaming VAD with Smart Turn confirming each pause; mid-sentence pauses merge
speech vad-stream call.wav --smart-turn
speech vad-stream call.wav --smart-turn --turn-threshold 0.6 --turn-max-silence 1.5

#include <speech_core/models/onnx_smart_turn.h>

speech_core::OnnxSmartTurn model("/models/smart-turn-v3.2-int8.onnx");

// Audio of the turn so far at any rate (resampled to 16 kHz internally).
float p = model.turn_complete_probability(turn.data(), turn.size(), rate);

// Or let the pipeline ask it on every VAD pause (before start()).
pipeline.set_turn_completion(&model);

speech download-models        # fetches the int8 graph with the other ONNX models
speech turn recording.wav --threshold 0.5 --json