From f77c5803f4d61099e572be8d877b1c4a4d6087cd Mon Sep 17 00:00:00 2001
From: yhliang <68215459+yhliang-aslp@users.noreply.github.com>
Date: 星期三, 10 五月 2023 12:02:06 +0800
Subject: [PATCH] Merge pull request #485 from alibaba-damo-academy/main
---
funasr/runtime/onnxruntime/src/audio.cpp | 42 ++++++++++++++++++++++++++++++++++++++++--
1 files changed, 40 insertions(+), 2 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/audio.cpp b/funasr/runtime/onnxruntime/src/audio.cpp
index d104500..6d63d67 100644
--- a/funasr/runtime/onnxruntime/src/audio.cpp
+++ b/funasr/runtime/onnxruntime/src/audio.cpp
@@ -11,6 +11,7 @@
using namespace std;
+namespace funasr {
// see http://soundfile.sapp.org/doc/WaveFormat/
// Note: We assume little endian here
struct WaveHeader {
@@ -237,6 +238,24 @@
LOG(ERROR) << "Failed to read " << filename;
return false;
}
+
+ if (!header.Validate()) {
+ return false;
+ }
+
+ header.SeekToDataChunk(is);
+ if (!is) {
+ return false;
+ }
+
+ if (!header.Validate()) {
+ return false;
+ }
+
+ header.SeekToDataChunk(is);
+ if (!is) {
+ return false;
+ }
*sampling_rate = header.sample_rate;
// header.subchunk2_size contains the number of bytes in the data.
@@ -380,8 +399,10 @@
FILE* fp;
fp = fopen(filename, "rb");
if (fp == nullptr)
+ {
LOG(ERROR) << "Failed to read " << filename;
return false;
+ }
fseek(fp, 0, SEEK_END);
uint32_t n_file_len = ftell(fp);
fseek(fp, 0, SEEK_SET);
@@ -494,7 +515,7 @@
delete frame;
}
-void Audio::Split(Model* recog_obj)
+void Audio::Split(OfflineStream* offline_stream)
{
AudioFrame *frame;
@@ -505,7 +526,7 @@
frame = NULL;
std::vector<float> pcm_data(speech_data, speech_data+sp_len);
- vector<std::vector<int>> vad_segments = recog_obj->VadSeg(pcm_data);
+ vector<std::vector<int>> vad_segments = (offline_stream->vad_handle)->Infer(pcm_data);
int seg_sample = MODEL_SAMPLE_RATE/1000;
for(vector<int> segment:vad_segments)
{
@@ -518,3 +539,20 @@
frame = NULL;
}
}
+
+
+void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments)
+{
+ AudioFrame *frame;
+
+ frame = frame_queue.front();
+ frame_queue.pop();
+ int sp_len = frame->GetLen();
+ delete frame;
+ frame = NULL;
+
+ std::vector<float> pcm_data(speech_data, speech_data+sp_len);
+ vad_segments = vad_obj->Infer(pcm_data);
+}
+
+} // namespace funasr
\ No newline at end of file
--
Gitblit v1.9.1