offline-speech-denoiser.h
1.5 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
// sherpa-onnx/csrc/offline-speech-denoiser.h
//
// Copyright (c) 2025 Xiaomi Corporation
#ifndef SHERPA_ONNX_CSRC_OFFLINE_SPEECH_DENOISER_H_
#define SHERPA_ONNX_CSRC_OFFLINE_SPEECH_DENOISER_H_
#include <memory>
#include <string>
#include <vector>
#include "sherpa-onnx/csrc/offline-speech-denoiser-model-config.h"
#include "sherpa-onnx/csrc/parse-options.h"
namespace sherpa_onnx {
struct DenoisedAudio {
std::vector<float> samples;
int32_t sample_rate;
};
struct OfflineSpeechDenoiserConfig {
OfflineSpeechDenoiserModelConfig model;
void Register(ParseOptions *po);
bool Validate() const;
std::string ToString() const;
};
class OfflineSpeechDenoiserImpl;
class OfflineSpeechDenoiser {
public:
explicit OfflineSpeechDenoiser(const OfflineSpeechDenoiserConfig &config);
~OfflineSpeechDenoiser();
template <typename Manager>
OfflineSpeechDenoiser(Manager *mgr,
const OfflineSpeechDenoiserConfig &config);
/*
* @param samples 1-D array of audio samples. Each sample is in the
* range [-1, 1].
* @param n Number of samples
* @param sample_rate Sample rate of the input samples
*
*/
DenoisedAudio Run(const float *samples, int32_t n, int32_t sample_rate) const;
/*
* Return the sample rate of the denoised audio
*/
int32_t GetSampleRate() const;
private:
std::unique_ptr<OfflineSpeechDenoiserImpl> impl_;
};
} // namespace sherpa_onnx
#endif // SHERPA_ONNX_CSRC_OFFLINE_SPEECH_DENOISER_H_