From 9ba0dbd98bf69c830dfcfde8f109a400cb65e4e5 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期五, 29 三月 2024 17:24:59 +0800
Subject: [PATCH] fix func Forward
---
runtime/onnxruntime/src/audio.cpp | 80 ++++++++++++++++++++++++++++++++++++++++
1 files changed, 80 insertions(+), 0 deletions(-)
diff --git a/runtime/onnxruntime/src/audio.cpp b/runtime/onnxruntime/src/audio.cpp
index 6f829cc..ef5d5f3 100644
--- a/runtime/onnxruntime/src/audio.cpp
+++ b/runtime/onnxruntime/src/audio.cpp
@@ -1023,6 +1023,32 @@
}
}
+int Audio::Fetch(float**& dout, int*& len, int*& flag, float*& start_time, int batch_size, int &batch_in)
+{
+ batch_in = std::min((int)frame_queue.size(), batch_size);
+ if (batch_in == 0){
+ return 0;
+ } else{
+ // init
+ dout = new float*[batch_in];
+ len = new int[batch_in];
+ flag = new int[batch_in];
+ start_time = new float[batch_in];
+
+ for(int idx=0; idx < batch_in; idx++){
+ AudioFrame *frame = frame_queue.front();
+ frame_queue.pop();
+
+ start_time[idx] = (float)(frame->GetStart())/ dest_sample_rate;
+ dout[idx] = speech_data + frame->GetStart();
+ len[idx] = frame->GetLen();
+ delete frame;
+ flag[idx] = S_END;
+ }
+ return 1;
+ }
+}
+
void Audio::Padding()
{
float num_samples = speech_len;
@@ -1085,6 +1111,60 @@
}
}
+void Audio::CutSplit(OfflineStream* offline_stream)
+{
+ std::unique_ptr<VadModel> vad_online_handle = make_unique<FsmnVadOnline>((FsmnVad*)(offline_stream->vad_handle).get());
+ AudioFrame *frame;
+
+ frame = frame_queue.front();
+ frame_queue.pop();
+ int sp_len = frame->GetLen();
+ delete frame;
+ frame = nullptr;
+
+ int step = dest_sample_rate*1;
+ bool is_final=false;
+ vector<std::vector<int>> vad_segments;
+ for (int sample_offset = 0; sample_offset < speech_len; sample_offset += std::min(step, speech_len - sample_offset)) {
+ if (sample_offset + step >= speech_len - 1) {
+ step = speech_len - sample_offset;
+ is_final = true;
+ } else {
+ is_final = false;
+ }
+ std::vector<float> pcm_data(speech_data+sample_offset, speech_data+sample_offset+step);
+ vector<std::vector<int>> cut_segments = vad_online_handle->Infer(pcm_data, is_final);
+ vad_segments.insert(vad_segments.end(), cut_segments.begin(), cut_segments.end());
+ }
+
+ int speech_start_i = -1, speech_end_i =-1;
+ for(vector<int> vad_segment:vad_segments)
+ {
+ if(vad_segment.size() != 2){
+ LOG(ERROR) << "Size of vad_segment is not 2.";
+ break;
+ }
+ if(vad_segment[0] != -1){
+ speech_start_i = vad_segment[0];
+ }
+ if(vad_segment[1] != -1){
+ speech_end_i = vad_segment[1];
+ }
+
+ if(speech_start_i!=-1 && speech_end_i!=-1){
+ frame = new AudioFrame();
+ int start = speech_start_i*seg_sample;
+ int end = speech_end_i*seg_sample;
+ frame->SetStart(start);
+ frame->SetEnd(end);
+ frame_queue.push(frame);
+ frame = nullptr;
+ speech_start_i=-1;
+ speech_end_i=-1;
+ }
+ }
+}
+
void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments, bool input_finished)
{
AudioFrame *frame;
--
Gitblit v1.9.1