deepgeek/silero-vad
2
0
Fork 0
mirror of https://github.com/snakers4/silero-vad.git synced 2026-02-05 18:09:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

fx issue https://github.com/snakers4/silero-vad/issues/67

Browse Source
This commit is contained in:
adamnsandle
2021-05-14 10:38:06 +00:00
parent 91648f32a8
commit b78f45a947
1 changed files with 13 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
utils_vad.py
View File

@@ -268,9 +268,18 @@ def get_speech_ts_adaptive(wav: torch.Tensor,
if visualize_probs: if visualize_probs:
pd.DataFrame({'probs': smoothed_probs}).plot(figsize=(16, 8)) pd.DataFrame({'probs': smoothed_probs}).plot(figsize=(16, 8))
for ts in speeches: for i, ts in enumerate(speeches):
ts['start'] = max(0, ts['start'] - speech_pad_samples) if i == 0:
ts['end'] += speech_pad_samples ts['start'] = max(0, ts['start'] - speech_pad_samples)
if i != len(speeches) - 1:
silence_duration = speeches[i+1]['start'] - ts['end']
if silence_duration < 2 * speech_pad_samples:
ts['end'] += silence_duration // 2
speeches[i+1]['start'] = max(0, speeches[i+1]['start'] - silence_duration // 2)
else:
ts['end'] += speech_pad_samples
else:
ts['end'] = min(len(wav), ts['end'] + speech_pad_samples)
return speeches return speeches