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

Support VITS VCTK models (#367)

Browse Source 
* Support VITS VCTK models

* Release v1.8.1
This commit is contained in:
Fangjun Kuang
2023-10-16 17:22:30 +08:00
committed by GitHub
parent d01682d968
commit 9efe69720d
16 changed files with 332 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
sherpa-onnx/csrc/offline-tts-vits-model-config.h
View File

@@ -16,12 +16,26 @@ struct OfflineTtsVitsModelConfig {
std::string lexicon;
std::string tokens;
float noise_scale = 0.667;
float noise_scale_w = 0.8;
float length_scale = 1;
// used only for multi-speaker models, e.g, vctk speech dataset.
// Not applicable for single-speaker models, e.g., ljspeech dataset
OfflineTtsVitsModelConfig() = default;
OfflineTtsVitsModelConfig(const std::string &model,
const std::string &lexicon,
const std::string &tokens)
: model(model), lexicon(lexicon), tokens(tokens) {}
const std::string &tokens,
float noise_scale = 0.667,
float noise_scale_w = 0.8, float length_scale = 1)
: model(model),
lexicon(lexicon),
tokens(tokens),
noise_scale(noise_scale),
noise_scale_w(noise_scale_w),
length_scale(length_scale) {}
void Register(ParseOptions *po);
bool Validate() const;