From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/runtime/onnxruntime/src/e2e-vad.h | 12 +++++++-----
1 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/e2e-vad.h b/funasr/runtime/onnxruntime/src/e2e-vad.h
index d881a32..a887db4 100644
--- a/funasr/runtime/onnxruntime/src/e2e-vad.h
+++ b/funasr/runtime/onnxruntime/src/e2e-vad.h
@@ -1,7 +1,10 @@
/**
* Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
* MIT License (https://opensource.org/licenses/MIT)
+ * Contributed by zhuzizyf(China Telecom).
*/
+
+#pragma once
#include <utility>
#include <vector>
@@ -13,7 +16,7 @@
#include <numeric>
#include <cassert>
-
+namespace funasr {
enum class VadStateMachine {
kVadInStateStartPointNotDetected = 1,
kVadInStateInSpeechSegment = 2,
@@ -303,7 +306,7 @@
max_end_sil_frame_cnt_thresh = max_end_sil - vad_opts.speech_to_sil_time_thres;
this->waveform = waveform;
this->vad_opts.max_single_segment_time = max_single_segment_time;
- this->vad_opts.speech_noise_thres = speech_noise_thres;
+ this->speech_noise_thres = speech_noise_thres;
this->vad_opts.sample_rate = sample_rate;
ComputeDecibel();
@@ -440,7 +443,7 @@
} else {
data_buf_all_size += waveform.size();
}
- for (int offset = 0; offset < waveform.size() - frame_sample_length + 1; offset += frame_shift_length) {
+ for (int offset = 0; offset + frame_sample_length -1 < waveform.size(); offset += frame_shift_length) {
float sum = 0.0;
for (int i = 0; i < frame_sample_length; i++) {
sum += waveform[offset + i] * waveform[offset + i];
@@ -779,5 +782,4 @@
};
-
-
+} // namespace funasr
--
Gitblit v1.9.1