Add C++ and Python API for Kokoro TTS models. (#1715)

This commit is contained in:
Fangjun Kuang
2025-01-16 14:24:51 +08:00
committed by GitHub
parent 9efe26a646
commit ffc6b480a0
27 changed files with 1193 additions and 29 deletions

View File

@@ -54,6 +54,7 @@ endif()
if(SHERPA_ONNX_ENABLE_TTS)
list(APPEND srcs
offline-tts-kokoro-model-config.cc
offline-tts-matcha-model-config.cc
offline-tts-model-config.cc
offline-tts-vits-model-config.cc

View File

@@ -0,0 +1,31 @@
// sherpa-onnx/python/csrc/offline-tts-kokoro-model-config.cc
//
// Copyright (c) 2025 Xiaomi Corporation
#include "sherpa-onnx/python/csrc/offline-tts-kokoro-model-config.h"
#include <string>
#include "sherpa-onnx/csrc/offline-tts-kokoro-model-config.h"
namespace sherpa_onnx {
void PybindOfflineTtsKokoroModelConfig(py::module *m) {
using PyClass = OfflineTtsKokoroModelConfig;
py::class_<PyClass>(*m, "OfflineTtsKokoroModelConfig")
.def(py::init<>())
.def(py::init<const std::string &, const std::string &,
const std::string &, const std::string &, float>(),
py::arg("model"), py::arg("voices"), py::arg("tokens"),
py::arg("data_dir"), py::arg("length_scale") = 1.0)
.def_readwrite("model", &PyClass::model)
.def_readwrite("voices", &PyClass::voices)
.def_readwrite("tokens", &PyClass::tokens)
.def_readwrite("data_dir", &PyClass::data_dir)
.def_readwrite("length_scale", &PyClass::length_scale)
.def("__str__", &PyClass::ToString)
.def("validate", &PyClass::Validate);
}
} // namespace sherpa_onnx

View File

@@ -0,0 +1,16 @@
// sherpa-onnx/python/csrc/offline-tts-kokoro-model-config.h
//
// Copyright (c) 2025 Xiaomi Corporation
#ifndef SHERPA_ONNX_PYTHON_CSRC_OFFLINE_TTS_KOKORO_MODEL_CONFIG_H_
#define SHERPA_ONNX_PYTHON_CSRC_OFFLINE_TTS_KOKORO_MODEL_CONFIG_H_
#include "sherpa-onnx/python/csrc/sherpa-onnx.h"
namespace sherpa_onnx {
void PybindOfflineTtsKokoroModelConfig(py::module *m);
}
#endif // SHERPA_ONNX_PYTHON_CSRC_OFFLINE_TTS_KOKORO_MODEL_CONFIG_H_

View File

@@ -7,6 +7,7 @@
#include <string>
#include "sherpa-onnx/csrc/offline-tts-model-config.h"
#include "sherpa-onnx/python/csrc/offline-tts-kokoro-model-config.h"
#include "sherpa-onnx/python/csrc/offline-tts-matcha-model-config.h"
#include "sherpa-onnx/python/csrc/offline-tts-vits-model-config.h"
@@ -15,20 +16,24 @@ namespace sherpa_onnx {
void PybindOfflineTtsModelConfig(py::module *m) {
PybindOfflineTtsVitsModelConfig(m);
PybindOfflineTtsMatchaModelConfig(m);
PybindOfflineTtsKokoroModelConfig(m);
using PyClass = OfflineTtsModelConfig;
py::class_<PyClass>(*m, "OfflineTtsModelConfig")
.def(py::init<>())
.def(py::init<const OfflineTtsVitsModelConfig &,
const OfflineTtsMatchaModelConfig &, int32_t, bool,
const OfflineTtsMatchaModelConfig &,
const OfflineTtsKokoroModelConfig &, int32_t, bool,
const std::string &>(),
py::arg("vits") = OfflineTtsVitsModelConfig{},
py::arg("matcha") = OfflineTtsMatchaModelConfig{},
py::arg("kokoro") = OfflineTtsKokoroModelConfig{},
py::arg("num_threads") = 1, py::arg("debug") = false,
py::arg("provider") = "cpu")
.def_readwrite("vits", &PyClass::vits)
.def_readwrite("matcha", &PyClass::matcha)
.def_readwrite("kokoro", &PyClass::kokoro)
.def_readwrite("num_threads", &PyClass::num_threads)
.def_readwrite("debug", &PyClass::debug)
.def_readwrite("provider", &PyClass::provider)