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

adapted pcm to 8k online

Browse Source
This commit is contained in:
雾聪 2023-12-13 17:30:38 +08:00
parent de87e1d180
commit 51f7b76660
3 changed files with 8 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
runtime/onnxruntime/bin/funasr-onnx-online-asr.cpp
View File

@ -112,7 +112,7 @@ int main(int argc, char *argv[])
auto& wav_file = wav_list[i];
auto& wav_id = wav_ids[i];
int32_t sampling_rate_ = -1;
int32_t sampling_rate_ = audio_fs.getValue();
funasr::Audio audio(1);
if(is_target_file(wav_file.c_str(), "wav")){
if(!audio.LoadWav2Char(wav_file.c_str(), &sampling_rate_)){
@ -145,7 +145,7 @@ int main(int argc, char *argv[])
is_final = false;
}
gettimeofday(&start, NULL);
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, audio_fs.getValue());
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, sampling_rate_);
gettimeofday(&end, NULL);
seconds = (end.tv_sec - start.tv_sec);
taking_micros += ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);

8
runtime/onnxruntime/bin/funasr-onnx-online-rtf.cpp
View File

@ -52,7 +52,7 @@ void runReg(FUNASR_HANDLE asr_handle, vector<string> wav_list, vector<string> wa
// warm up
for (size_t i = 0; i < 10; i++)
{
int32_t sampling_rate_ = -1;
int32_t sampling_rate_ = audio_fs;
funasr::Audio audio(1);
if(is_target_file(wav_list[0].c_str(), "wav")){
if(!audio.LoadWav2Char(wav_list[0].c_str(), &sampling_rate_)){
@ -84,7 +84,7 @@ void runReg(FUNASR_HANDLE asr_handle, vector<string> wav_list, vector<string> wa
} else {
is_final = false;
}
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, audio_fs);
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, sampling_rate_);
if (result)
{
FunASRFreeResult(result);
@ -98,7 +98,7 @@ void runReg(FUNASR_HANDLE asr_handle, vector<string> wav_list, vector<string> wa
if (i >= wav_list.size()) {
break;
}
int32_t sampling_rate_ = -1;
int32_t sampling_rate_ = audio_fs;
funasr::Audio audio(1);
if(is_target_file(wav_list[i].c_str(), "wav")){
if(!audio.LoadWav2Char(wav_list[i].c_str(), &sampling_rate_)){
@ -131,7 +131,7 @@ void runReg(FUNASR_HANDLE asr_handle, vector<string> wav_list, vector<string> wa
is_final = false;
}
gettimeofday(&start, NULL);
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, audio_fs);
FUNASR_RESULT result = FunASRInferBuffer(online_handle, speech_buff+sample_offset, step, RASR_NONE, NULL, is_final, sampling_rate_);
gettimeofday(&end, NULL);
seconds = (end.tv_sec - start.tv_sec);
long taking_micros = ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);

5
runtime/onnxruntime/bin/funasr-onnx-online-vad.cpp
View File

@ -141,10 +141,9 @@ int main(int argc, char *argv[])
auto& wav_file = wav_list[i];
auto& wav_id = wav_ids[i];
int32_t sampling_rate_ = -1;
int32_t sampling_rate_ = audio_fs.getValue();
funasr::Audio audio(1);
if(is_target_file(wav_file.c_str(), "wav")){
int32_t sampling_rate_ = -1;
if(!audio.LoadWav2Char(wav_file.c_str(), &sampling_rate_)){
LOG(ERROR)<<"Failed to load "<< wav_file;
exit(-1);
@ -172,7 +171,7 @@ int main(int argc, char *argv[])
is_final = false;
}
gettimeofday(&start, NULL);
FUNASR_RESULT result = FsmnVadInferBuffer(online_hanlde, speech_buff+sample_offset, step, NULL, is_final, audio_fs.getValue());
FUNASR_RESULT result = FsmnVadInferBuffer(online_hanlde, speech_buff+sample_offset, step, NULL, is_final, sampling_rate_);
gettimeofday(&end, NULL);
seconds = (end.tv_sec - start.tv_sec);
taking_micros += ((seconds * 1000000) + end.tv_usec) - (start.tv_usec);