Merge pull request #199 from snakers4/adamnsandle

fx end of chunk may exceed audio length
snakers4 · Jun 2, 2022 · 7c671a7 · 7c671a7
2 parents 900c71a + 8eba346
commit 7c671a7
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/utils_vad.py b/utils_vad.py
@@ -252,8 +252,8 @@ def get_speech_timestamps(audio: torch.Tensor,
                 speech['end'] += int(silence_duration // 2)
                 speeches[i+1]['start'] = int(max(0, speeches[i+1]['start'] - silence_duration // 2))
             else:
-                speech['end'] += int(speech_pad_samples)
-                speeches[i+1]['start'] -= int(speech_pad_samples)
+                speech['end'] = int(min(audio_length_samples, speech['end'] + speech_pad_samples))
+                speeches[i+1]['start'] = int(max(0, speeches[i+1]['start'] - speech_pad_samples))
         else:
             speech['end'] = int(min(audio_length_samples, speech['end'] + speech_pad_samples))