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

9
python-api-examples/generate-subtitles.py
View File

@@ -406,7 +406,14 @@ def main():
config = sherpa_onnx.VadModelConfig()
config.silero_vad.model = args.silero_vad_model
config.silero_vad.min_silence_duration = 0.25
config.silero_vad.threshold = 0.5
config.silero_vad.min_silence_duration = 0.25 # seconds
config.silero_vad.min_speech_duration = 0.25 # seconds
# If the current segment is larger than this value, then it increases
# the threshold to 0.9 internally. After detecting this segment,
# it resets the threshold to its original value.
config.silero_vad.max_speech_duration = 5 # seconds
config.sample_rate = args.sample_rate
window_size = config.silero_vad.window_size