From c2dee5e3c29eba79e591d9e9caebaef15ea4e56b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期四, 29 六月 2023 11:09:28 +0800
Subject: [PATCH] Merge pull request #687 from alibaba-damo-academy/dev_lhn
---
funasr/runtime/onnxruntime/src/audio.cpp | 116 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 109 insertions(+), 7 deletions(-)
diff --git a/funasr/runtime/onnxruntime/src/audio.cpp b/funasr/runtime/onnxruntime/src/audio.cpp
index 8f46a4f..23d0010 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 {
@@ -175,12 +176,12 @@
{
if (speech_buff != NULL) {
free(speech_buff);
-
}
-
if (speech_data != NULL) {
-
free(speech_data);
+ }
+ if (speech_char != NULL) {
+ free(speech_char);
}
}
@@ -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.
@@ -277,8 +296,47 @@
return false;
}
-bool Audio::LoadWav(const char* buf, int n_file_len, int32_t* sampling_rate)
+bool Audio::LoadWav2Char(const char *filename, int32_t* sampling_rate)
{
+ WaveHeader header;
+ if (speech_char != NULL) {
+ free(speech_char);
+ }
+ offset = 0;
+ std::ifstream is(filename, std::ifstream::binary);
+ is.read(reinterpret_cast<char *>(&header), sizeof(header));
+ if(!is){
+ 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.
+ // As we assume each sample contains two bytes, so it is divided by 2 here
+ speech_len = header.subchunk2_size / 2;
+ speech_char = (char *)malloc(header.subchunk2_size);
+ memset(speech_char, 0, header.subchunk2_size);
+ is.read(speech_char, header.subchunk2_size);
+
+ return true;
+}
+
+bool Audio::LoadWav(const char* buf, int n_file_len, int32_t* sampling_rate)
+{
WaveHeader header;
if (speech_data != NULL) {
free(speech_data);
@@ -422,6 +480,33 @@
}
+bool Audio::LoadPcmwav2Char(const char* filename, int32_t* sampling_rate)
+{
+ if (speech_char != NULL) {
+ free(speech_char);
+ }
+ offset = 0;
+
+ 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);
+
+ speech_len = (n_file_len) / 2;
+ speech_char = (char *)malloc(n_file_len);
+ memset(speech_char, 0, n_file_len);
+ fread(speech_char, sizeof(int16_t), n_file_len/2, fp);
+ fclose(fp);
+
+ return true;
+}
+
int Audio::FetchChunck(float *&dout, int len)
{
if (offset >= speech_align_len) {
@@ -496,7 +581,7 @@
delete frame;
}
-void Audio::Split(Model* recog_obj)
+void Audio::Split(OfflineStream* offline_stream)
{
AudioFrame *frame;
@@ -507,7 +592,7 @@
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)
{
@@ -519,4 +604,21 @@
frame_queue.push(frame);
frame = NULL;
}
-}
\ No newline at end of file
+}
+
+
+void Audio::Split(VadModel* vad_obj, vector<std::vector<int>>& vad_segments, bool input_finished)
+{
+ 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, input_finished);
+}
+
+} // namespace funasr
\ No newline at end of file
--
Gitblit v1.9.1