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

Add APIs about max speech duration in VAD for various programming languages (#1349)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-09-14 12:30:13 +08:00
committed by GitHub
parent 1423ddb1f0
commit e7ffcbd677
31 changed files with 88 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
sherpa-onnx/c-api/c-api.cc
View File

@@ -907,6 +907,9 @@ SherpaOnnxVoiceActivityDetector *SherpaOnnxCreateVoiceActivityDetector(
vad_config.silero_vad.window_size =
SHERPA_ONNX_OR(config->silero_vad.window_size, 512);
vad_config.silero_vad.max_speech_duration =
SHERPA_ONNX_OR(config->silero_vad.max_speech_duration, 20);
vad_config.sample_rate = SHERPA_ONNX_OR(config->sample_rate, 16000);
vad_config.num_threads = SHERPA_ONNX_OR(config->num_threads, 1);
vad_config.provider = SHERPA_ONNX_OR(config->provider, "cpu");

5
sherpa-onnx/c-api/c-api.h
View File

@@ -746,6 +746,11 @@ SHERPA_ONNX_API typedef struct SherpaOnnxSileroVadModelConfig {
float min_speech_duration;
int window_size;
// If a speech segment is longer than this value, then we increase
// the threshold to 0.9. After finishing detecting the segment,
// the threshold value is reset to its original value.
float max_speech_duration;
} SherpaOnnxSileroVadModelConfig;
SHERPA_ONNX_API typedef struct SherpaOnnxVadModelConfig {