offline-tts-vits-model.h
1.6 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
// sherpa-onnx/csrc/offline-tts-vits-model.h
//
// Copyright (c) 2023 Xiaomi Corporation
#ifndef SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_H_
#define SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_H_
#include <memory>
#include <string>
#if __ANDROID_API__ >= 9
#include "android/asset_manager.h"
#include "android/asset_manager_jni.h"
#endif
#include "onnxruntime_cxx_api.h" // NOLINT
#include "sherpa-onnx/csrc/offline-tts-model-config.h"
#include "sherpa-onnx/csrc/offline-tts-vits-model-metadata.h"
namespace sherpa_onnx {
class OfflineTtsVitsModel {
public:
~OfflineTtsVitsModel();
explicit OfflineTtsVitsModel(const OfflineTtsModelConfig &config);
#if __ANDROID_API__ >= 9
OfflineTtsVitsModel(AAssetManager *mgr, const OfflineTtsModelConfig &config);
#endif
/** Run the model.
*
* @param x A int64 tensor of shape (1, num_tokens)
// @param sid Speaker ID. Used only for multi-speaker models, e.g., models
// trained using the VCTK dataset. It is not used for
// single-speaker models, e.g., models trained using the ljspeech
// dataset.
* @return Return a float32 tensor containing audio samples. You can flatten
* it to a 1-D tensor.
*/
Ort::Value Run(Ort::Value x, int64_t sid = 0, float speed = 1.0);
// This is for MeloTTS
Ort::Value Run(Ort::Value x, Ort::Value tones, int64_t sid = 0,
float speed = 1.0);
const OfflineTtsVitsModelMetaData &GetMetaData() const;
private:
class Impl;
std::unique_ptr<Impl> impl_;
};
} // namespace sherpa_onnx
#endif // SHERPA_ONNX_CSRC_OFFLINE_TTS_VITS_MODEL_H_