speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Expose the max_end_silence_time to the user (#1532)

Browse Source
This commit is contained in:
BOBOTANG 2024-03-22 19:10:44 +08:00 committed by GitHub
parent 9c0735b7df
commit a6a9d29bbd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
funasr/models/fsmn_vad_streaming/model.py
View File

@ -543,6 +543,11 @@ class FsmnVADStreaming(nn.Module):
cache["frontend"] = {}
cache["prev_samples"] = torch.empty(0)
cache["encoder"] = {}
if kwargs.get("max_end_silence_time") is not None:
# update the max_end_silence_time
self.vad_opts.max_end_silence_time = kwargs.get("max_end_silence_time")
windows_detector = WindowDetector(self.vad_opts.window_size_ms,
self.vad_opts.sil_to_speech_time_thres,
self.vad_opts.speech_to_sil_time_thres,