From b3fcd42bf6e60372ed0f0d3e53798fcdd713fe08 Mon Sep 17 00:00:00 2001
From: Shi Xian <40013335+R1ckShi@users.noreply.github.com>
Date: 星期三, 06 十二月 2023 11:14:57 +0800
Subject: [PATCH] Merge pull request #1144 from yeyupiaoling/main
---
funasr/bin/vad_infer.py | 10 ++++++----
1 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/funasr/bin/vad_infer.py b/funasr/bin/vad_infer.py
index c60a8f1..5763873 100644
--- a/funasr/bin/vad_infer.py
+++ b/funasr/bin/vad_infer.py
@@ -23,9 +23,9 @@
"""Speech2VadSegment class
Examples:
- >>> import soundfile
+ >>> import librosa
>>> speech2segment = Speech2VadSegment("vad_config.yml", "vad.pt")
- >>> audio, rate = soundfile.read("speech.wav")
+ >>> audio, rate = librosa.load("speech.wav")
>>> speech2segment(audio)
[[10, 230], [245, 450], ...]
@@ -118,9 +118,9 @@
"""Speech2VadSegmentOnline class
Examples:
- >>> import soundfile
+ >>> import librosa
>>> speech2segment = Speech2VadSegmentOnline("vad_config.yml", "vad.pt")
- >>> audio, rate = soundfile.read("speech.wav")
+ >>> audio, rate = librosa.load("speech.wav")
>>> speech2segment(audio)
[[10, 230], [245, 450], ...]
@@ -162,6 +162,8 @@
feats = to_device(feats, device=self.device)
feats_len = feats_len.int()
waveforms = self.frontend.get_waveforms()
+ if max_end_sil == 800 and self.vad_infer_args.vad_post_conf["max_end_silence_time"] != 800:
+ max_end_sil = self.vad_infer_args.vad_post_conf["max_end_silence_time"]
batch = {
"feats": feats,
--
Gitblit v1.9.1