diarization.h

/* Copyright 2021 ID R&D Inc. All Rights Reserved. */
 
#pragma once
 
#include <string>
#include <vector>
#include <memory>
#include <map>
#include <voicesdk/core/common/intervals.h>
 
namespace voicesdk {
namespace diar {
 
using TimeStamps = std::map<size_t, std::vector<AudioInterval>>;
 
class VOICE_SDK_API DiarizationEngine {
public:
    using Ptr = std::shared_ptr<DiarizationEngine>;
 
    static DiarizationEngine::Ptr Create(const std::string& init_dir);
 
    virtual ~DiarizationEngine() {}
 
 
    virtual TimeStamps GetSegmentation(const float* float_samples, const size_t samples_num, const size_t sample_rate,
                                       const size_t num_speakers = 0) = 0;
 
    virtual TimeStamps GetSegmentation(const int16_t* pcm16_samples, const size_t samples_num, const size_t sample_rate,
                                       const size_t num_speakers = 0) = 0;
 
    virtual TimeStamps GetSegmentation(const uint8_t* pcm16_bytes, const size_t bytes_num, const size_t sample_rate,
                                       const size_t num_speakers = 0) = 0;
 
    virtual TimeStamps GetSegmentation(const std::string& audio_path, const size_t num_speakers = 0) = 0;
};
 
}  // namespace diar
}  // namespace voicesdk