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

@@ -10,8 +10,9 @@
#include <vector>
#include "sherpa-onnx/csrc/offline-tts-frontend.h"
#include "sherpa-onnx/csrc/offline-tts-matcha-model-metadata.h"
#include "sherpa-onnx/csrc/offline-tts-vits-model-metadata.h"
#include "sherpa-onnx/csrc/offline-tts-kokoro-model-meta-data.h"
#include "sherpa-onnx/csrc/offline-tts-matcha-model-meta-data.h"
#include "sherpa-onnx/csrc/offline-tts-vits-model-meta-data.h"
namespace sherpa_onnx {
@@ -23,6 +24,9 @@ class PiperPhonemizeLexicon : public OfflineTtsFrontend {
PiperPhonemizeLexicon(const std::string &tokens, const std::string &data_dir,
const OfflineTtsMatchaModelMetaData &matcha_meta_data);
PiperPhonemizeLexicon(const std::string &tokens, const std::string &data_dir,
const OfflineTtsKokoroModelMetaData &kokoro_meta_data);
template <typename Manager>
PiperPhonemizeLexicon(Manager *mgr, const std::string &tokens,
const std::string &data_dir,
@@ -33,6 +37,11 @@ class PiperPhonemizeLexicon : public OfflineTtsFrontend {
const std::string &data_dir,
const OfflineTtsMatchaModelMetaData &matcha_meta_data);
template <typename Manager>
PiperPhonemizeLexicon(Manager *mgr, const std::string &tokens,
const std::string &data_dir,
const OfflineTtsKokoroModelMetaData &kokoro_meta_data);
std::vector<TokenIDs> ConvertTextToTokenIds(
const std::string &text, const std::string &voice = "") const override;
@@ -43,12 +52,17 @@ class PiperPhonemizeLexicon : public OfflineTtsFrontend {
std::vector<TokenIDs> ConvertTextToTokenIdsMatcha(
const std::string &text, const std::string &voice = "") const;
std::vector<TokenIDs> ConvertTextToTokenIdsKokoro(
const std::string &text, const std::string &voice = "") const;
private:
// map unicode codepoint to an integer ID
std::unordered_map<char32_t, int32_t> token2id_;
OfflineTtsVitsModelMetaData vits_meta_data_;
OfflineTtsMatchaModelMetaData matcha_meta_data_;
OfflineTtsKokoroModelMetaData kokoro_meta_data_;
bool is_matcha_ = false;
bool is_kokoro_ = false;
};
} // namespace sherpa_onnx