p99 ו VAP - מודלים של Turn-take

import SpeechVAD

let p99 = try await P99TurnModel.fromPretrained()
let session = try p99.createSession()
let frames = try session.pushAudio(pcm16k)
for frame in frames {
    print(frame.probability, frame.availableAfterSeconds)
}
try session.reset()

let vap = try await VAPModel.fromPretrained()
let forecast = try vap.forecast(userAudio: userPcm, agentAudio: agentPcm)
print(forecast.pNow, forecast.pFuture, forecast.voiceActivity)

#include <speech_core/models/onnx_vap.h>

speech_core::OnnxVap model("models/vap.onnx");
auto forecast = model.forecast(user.data(), agent.data(), user.size(), 16000);
// p_now[0]: user, p_now[1]: agent
// p_future and voice_activity use the same channel order.

val directory = ModelManager.ensureVapModels(context)
withContext(Dispatchers.Default) {
    VoiceActivityProjection(VoiceActivityProjectionConfig(directory)).use { model ->
        val forecast = model.forecast(userPcm, agentPcm)
        println(forecast.userNearTerm)
        println(forecast.agentNearTerm)
    }
}