From 8eba346bc94cb4157ba561f31bf14120e8effde3 Mon Sep 17 00:00:00 2001 From: adamnsandle Date: Thu, 2 Jun 2022 10:39:16 +0000 Subject: [PATCH] fx end of chunk may exceed audio length --- utils_vad.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/utils_vad.py b/utils_vad.py index b390cf6..80db3c9 100644 --- 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))