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

Support specifying max speech duration for VAD. (#1348)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-09-14 10:57:46 +08:00
committed by GitHub
parent 5d761712db
commit 1423ddb1f0
5 changed files with 70 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
sherpa-onnx/python/csrc/silero-vad-model-config.cc
View File

@@ -17,7 +17,8 @@ void PybindSileroVadModelConfig(py::module *m) {
.def(py::init<>())
.def(py::init([](const std::string &model, float threshold,
float min_silence_duration, float min_speech_duration,
int32_t window_size) -> std::unique_ptr<PyClass> {
int32_t window_size,
float max_speech_duration) -> std::unique_ptr<PyClass> {
auto ans = std::make_unique<PyClass>();
ans->model = model;
@@ -25,17 +26,20 @@ void PybindSileroVadModelConfig(py::module *m) {
ans->min_silence_duration = min_silence_duration;
ans->min_speech_duration = min_speech_duration;
ans->window_size = window_size;
ans->max_speech_duration = max_speech_duration;
return ans;
}),
py::arg("model"), py::arg("threshold") = 0.5,
py::arg("min_silence_duration") = 0.5,
py::arg("min_speech_duration") = 0.25, py::arg("window_size") = 512)
py::arg("min_speech_duration") = 0.25, py::arg("window_size") = 512,
py::arg("max_speech_duration") = 20)
.def_readwrite("model", &PyClass::model)
.def_readwrite("threshold", &PyClass::threshold)
.def_readwrite("min_silence_duration", &PyClass::min_silence_duration)
.def_readwrite("min_speech_duration", &PyClass::min_speech_duration)
.def_readwrite("window_size", &PyClass::window_size)
.def_readwrite("max_speech_duration", &PyClass::max_speech_duration)
.def("__str__", &PyClass::ToString)
.def("validate", &PyClass::Validate);
}