speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #242 from RapidAI/main

Browse Source 
Bugfix and Tidy up
This commit is contained in:
zhifu gao 2023-03-16 13:05:31 +08:00 committed by GitHub
commit d1cde93914
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 63 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
funasr/runtime/onnxruntime/src/Audio.cpp
View File

@ -237,7 +237,7 @@ bool Audio::loadpcmwav(const char* buf, int nBufLen)
size_t nOffset = 0; size_t nOffset = 0;
#define WAV_HEADER_SIZE 44
speech_len = nBufLen / 2; speech_len = nBufLen / 2;
speech_align_len = (int)(ceil((float)speech_len / align_size) * align_size); speech_align_len = (int)(ceil((float)speech_len / align_size) * align_size);
@ -263,7 +263,8 @@ bool Audio::loadpcmwav(const char* buf, int nBufLen)
speech_data[i] = (float)speech_buff[i] / scale; speech_data[i] = (float)speech_buff[i] / scale;
} }
AudioFrame* frame = new AudioFrame(speech_len);
frame_queue.push(frame);
return true; return true;
} }

17
funasr/runtime/onnxruntime/src/librapidasrapi.cpp
View File

@ -26,8 +26,9 @@ extern "C" {
return nullptr; return nullptr;
Audio audio(1); Audio audio(1);
audio.loadwav(szBuf,nLen); if (!audio.loadwav(szBuf, nLen))
audio.split(); return nullptr;
//audio.split();
float* buff; float* buff;
int len; int len;
@ -58,8 +59,9 @@ extern "C" {
return nullptr; return nullptr;
Audio audio(1); Audio audio(1);
audio.loadpcmwav(szBuf, nLen); if (!audio.loadpcmwav(szBuf, nLen))
audio.split(); return nullptr;
//audio.split();
float* buff; float* buff;
int len; int len;
@ -91,8 +93,9 @@ extern "C" {
return nullptr; return nullptr;
Audio audio(1); Audio audio(1);
audio.loadpcmwav(szFileName); if (!audio.loadpcmwav(szFileName))
audio.split(); return nullptr;
//audio.split();
float* buff; float* buff;
int len; int len;
@ -125,7 +128,7 @@ extern "C" {
Audio audio(1); Audio audio(1);
if(!audio.loadwav(szWavfile)) if(!audio.loadwav(szWavfile))
return nullptr; return nullptr;
audio.split(); //audio.split();
float* buff; float* buff;
int len; int len;

57
funasr/runtime/onnxruntime/tester/tester.cpp
View File

@ -8,7 +8,7 @@
#include "librapidasrapi.h" #include "librapidasrapi.h"
#include <iostream> #include <iostream>
#include <fstream>
using namespace std; using namespace std;
int main(int argc, char *argv[]) int main(int argc, char *argv[])
@ -40,10 +40,13 @@ int main(int argc, char *argv[])
gettimeofday(&start, NULL); gettimeofday(&start, NULL);
RPASR_RESULT Result=RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
gettimeofday(&end, NULL);
float snippet_time = 0.0f; float snippet_time = 0.0f;
RPASR_RESULT Result=RapidAsrRecogFile(AsrHanlde, argv[2], RASR_NONE, NULL);
gettimeofday(&end, NULL);
if (Result) if (Result)
{ {
string msg = RapidAsrGetResult(Result, 0); string msg = RapidAsrGetResult(Result, 0);
@ -56,11 +59,51 @@ int main(int argc, char *argv[])
} }
else else
{ {
cout <<("no return data!"); cout <<"no return data!";
} }
printf("Audio length %lfs.\n", (double)snippet_time);
//char* buff = nullptr;
//int len = 0;
//ifstream ifs(argv[2], std::ios::binary | std::ios::in);
//if (ifs.is_open())
//{
// ifs.seekg(0, std::ios::end);
// len = ifs.tellg();
// ifs.seekg(0, std::ios::beg);
// buff = new char[len];
// ifs.read(buff, len);
// //RPASR_RESULT Result = RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
// RPASR_RESULT Result=RapidAsrRecogPCMBuffer(AsrHanlde, buff,len, RASR_NONE, NULL);
// //RPASR_RESULT Result = RapidAsrRecogPCMFile(AsrHanlde, argv[2], RASR_NONE, NULL);
// gettimeofday(&end, NULL);
//
// if (Result)
// {
// string msg = RapidAsrGetResult(Result, 0);
// setbuf(stdout, NULL);
// cout << "Result: \"";
// cout << msg << endl;
// cout << "\"." << endl;
// snippet_time = RapidAsrGetRetSnippetTime(Result);
// RapidAsrFreeResult(Result);
// }
// else
// {
// cout <<"no return data!";
// }
//
//delete[]buff;
//}
printf("Audio length %lfs.\n", (double)snippet_time);
seconds = (end.tv_sec - start.tv_sec); seconds = (end.tv_sec - start.tv_sec);
long taking_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec); long taking_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);
printf("Model inference takes %lfs.\n", (double)taking_micros / 1000000); printf("Model inference takes %lfs.\n", (double)taking_micros / 1000000);