Configuration for a Ten VAD model.
More...
#include <c-api.h>
Definition at line 1869 of file c-api.h.
◆ max_speech_duration
| float SherpaOnnxTenVadModelConfig::max_speech_duration |
Maximum speech duration in seconds.
When a segment exceeds this value, the detector temporarily uses a higher threshold to encourage a split.
Definition at line 1886 of file c-api.h.
◆ min_silence_duration
| float SherpaOnnxTenVadModelConfig::min_silence_duration |
Minimum silence duration in seconds used to close a speech segment.
Definition at line 1875 of file c-api.h.
◆ min_speech_duration
| float SherpaOnnxTenVadModelConfig::min_speech_duration |
Minimum speech duration in seconds to keep a detected segment.
Definition at line 1877 of file c-api.h.
◆ model
| const char* SherpaOnnxTenVadModelConfig::model |
Path to ten-vad.onnx.
Definition at line 1871 of file c-api.h.
◆ threshold
| float SherpaOnnxTenVadModelConfig::threshold |
Speech probability threshold. Frames above this value are speech.
Definition at line 1873 of file c-api.h.
◆ window_size
| int32_t SherpaOnnxTenVadModelConfig::window_size |
Input window size in samples. A common value is 256.
Definition at line 1879 of file c-api.h.
The documentation for this struct was generated from the following file: