EngineX-Iluvatar/enginex_bi_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add C++ runtime for Matcha-TTS (#1627)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-12-31 12:44:14 +08:00
committed by GitHub
parent 5c2cc48f50
commit 2c2926af7d
33 changed files with 1397 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
sherpa-onnx/csrc/offline-tts-vits-impl.h
View File

@@ -156,17 +156,31 @@ class OfflineTtsVitsImpl : public OfflineTtsImpl {
int32_t num_speakers = meta_data.num_speakers;
if (num_speakers == 0 && sid != 0) {
#if __OHOS__
SHERPA_ONNX_LOGE(
"This is a single-speaker model and supports only sid 0. Given sid: "
"%{public}d. sid is ignored",
static_cast<int32_t>(sid));
#else
SHERPA_ONNX_LOGE(
"This is a single-speaker model and supports only sid 0. Given sid: "
"%d. sid is ignored",
static_cast<int32_t>(sid));
#endif
}
if (num_speakers != 0 && (sid >= num_speakers || sid < 0)) {
#if __OHOS__
SHERPA_ONNX_LOGE(
"This model contains only %{public}d speakers. sid should be in the "
"range [%{public}d, %{public}d]. Given: %{public}d. Use sid=0",
num_speakers, 0, num_speakers - 1, static_cast<int32_t>(sid));
#else
SHERPA_ONNX_LOGE(
"This model contains only %d speakers. sid should be in the range "
"[%d, %d]. Given: %d. Use sid=0",
num_speakers, 0, num_speakers - 1, static_cast<int32_t>(sid));
#endif
sid = 0;
}
@@ -389,8 +403,7 @@ class OfflineTtsVitsImpl : public OfflineTtsImpl {
} else if (meta_data.jieba && !config_.model.vits.dict_dir.empty()) {
frontend_ = std::make_unique<JiebaLexicon>(
config_.model.vits.lexicon, config_.model.vits.tokens,
config_.model.vits.dict_dir, model_->GetMetaData(),
config_.model.debug);
config_.model.vits.dict_dir, config_.model.debug);
} else if ((meta_data.is_piper || meta_data.is_coqui ||
meta_data.is_icefall) &&
!config_.model.vits.data_dir.empty()) {
@@ -410,17 +423,6 @@ class OfflineTtsVitsImpl : public OfflineTtsImpl {
}
}
std::vector<int64_t> AddBlank(const std::vector<int64_t> &x) const {
// we assume the blank ID is 0
std::vector<int64_t> buffer(x.size() * 2 + 1);
int32_t i = 1;
for (auto k : x) {
buffer[i] = k;
i += 2;
}
return buffer;
}
GeneratedAudio Process(const std::vector<std::vector<int64_t>> &tokens,
const std::vector<std::vector<int64_t>> &tones,
int32_t sid, float speed) const {