From 4af0c1e2ce6b791b73f1d7ae77dc8d9c7d76f5c0 Mon Sep 17 00:00:00 2001 From: wenbindu Date: Wed, 28 May 2025 10:59:59 +0800 Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9=E6=B3=A8=E9=87=8A?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- main/xiaozhi-server/core/providers/vad/silero.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/main/xiaozhi-server/core/providers/vad/silero.py b/main/xiaozhi-server/core/providers/vad/silero.py index 8ec1f6eb..63a26cd2 100644 --- a/main/xiaozhi-server/core/providers/vad/silero.py +++ b/main/xiaozhi-server/core/providers/vad/silero.py @@ -18,7 +18,7 @@ class VADProvider(VADProviderBase): model="silero_vad", force_reload=False, ) - (get_speech_timestamps, _, _, _, _) = self.utils + get_speech_timestamps, *_ = self.utils self.decoder = opuslib_next.Decoder(16000, 1) @@ -53,7 +53,7 @@ class VADProvider(VADProviderBase): speech_prob = self.model(audio_tensor, 16000).item() client_have_voice = speech_prob >= self.vad_threshold - # 如果之前有声音，但本次没有声音，且与上次有声音的时间查已经超过了静默阈值，则认为已经说完一句话 + # 如果之前有声音，但本次没有声音，且与上次有声音的时间差已经超过了静默阈值，则认为已经说完一句话 if conn.client_have_voice and not client_have_voice: stop_duration = ( time.time() * 1000 - conn.client_have_voice_last_time