hnluo
2023-09-21 bf4b3ef9cb95acaa2b92b98f236c4f3228cdbc2d
funasr/runtime/onnxruntime/src/audio.cpp
@@ -9,6 +9,11 @@
#include "audio.h"
#include "precomp.h"
#if defined(__APPLE__)
#include <string.h>
#else
extern "C" {
#include <libavutil/opt.h>
#include <libavcodec/avcodec.h>
@@ -17,6 +22,10 @@
#include <libavutil/samplefmt.h>
#include <libswresample/swresample.h>
}
#endif
using namespace std;
@@ -245,6 +254,9 @@
}
bool Audio::FfmpegLoad(const char *filename, bool copy2char){
#if defined(__APPLE__)
    return false;
#else
    // from file
    AVFormatContext* formatContext = avformat_alloc_context();
    if (avformat_open_input(&formatContext, filename, NULL, NULL) != 0) {
@@ -403,10 +415,13 @@
    }
    else
        return false;
#endif
}
bool Audio::FfmpegLoad(const char* buf, int n_file_len){
#if defined(__APPLE__)
    return false;
#else
    // from buf
    char* buf_copy = (char *)malloc(n_file_len);
    memcpy(buf_copy, buf, n_file_len);
@@ -577,7 +592,7 @@
    }
    else
        return false;
#endif
}
@@ -1097,6 +1112,8 @@
            if(asr_mode != ASR_OFFLINE){
                if(buff_len >= step){
                    frame = new AudioFrame(step);
                    frame->global_start = speech_start;
                    frame->global_end = speech_start + step/seg_sample;
                    frame->data = (float*)malloc(sizeof(float) * step);
                    memcpy(frame->data, all_samples.data()+start-offset, step*sizeof(float));
                    asr_online_queue.push(frame);
@@ -1123,6 +1140,8 @@
                if(asr_mode != ASR_OFFLINE){
                    frame = new AudioFrame(end-start);
                    frame->is_final = true;
                    frame->global_start = speech_start_i;
                    frame->global_end = speech_end_i;
                    frame->data = (float*)malloc(sizeof(float) * (end-start));
                    memcpy(frame->data, all_samples.data()+start-offset, (end-start)*sizeof(float));
                    asr_online_queue.push(frame);
@@ -1132,6 +1151,8 @@
                if(asr_mode != ASR_ONLINE){
                    frame = new AudioFrame(end-start);
                    frame->is_final = true;
                    frame->global_start = speech_start_i;
                    frame->global_end = speech_end_i;
                    frame->data = (float*)malloc(sizeof(float) * (end-start));
                    memcpy(frame->data, all_samples.data()+start-offset, (end-start)*sizeof(float));
                    asr_offline_queue.push(frame);
@@ -1153,6 +1174,8 @@
                if(asr_mode != ASR_OFFLINE){
                    if(buff_len >= step){
                        frame = new AudioFrame(step);
                        frame->global_start = speech_start;
                        frame->global_end = speech_start + step/seg_sample;
                        frame->data = (float*)malloc(sizeof(float) * step);
                        memcpy(frame->data, all_samples.data()+start-offset, step*sizeof(float));
                        asr_online_queue.push(frame);
@@ -1163,8 +1186,8 @@
            }else if(speech_end_i != -1){ // [-1,100]
                if(speech_start == -1 or speech_offline_start == -1){
                    LOG(ERROR) <<"Vad start is null while vad end is available." ;
                    exit(-1);
                    LOG(ERROR) <<"Vad start is null while vad end is available. Set vad start 0" ;
                    speech_start = 0;
                }
                int start = speech_start*seg_sample;
@@ -1176,6 +1199,8 @@
                if(asr_mode != ASR_ONLINE){
                    frame = new AudioFrame(end-offline_start);
                    frame->is_final = true;
                    frame->global_start = speech_offline_start;
                    frame->global_end = speech_end_i;
                    frame->data = (float*)malloc(sizeof(float) * (end-offline_start));
                    memcpy(frame->data, all_samples.data()+offline_start-offset, (end-offline_start)*sizeof(float));
                    asr_offline_queue.push(frame);
@@ -1192,6 +1217,8 @@
                            }
                            frame = new AudioFrame(step);
                            frame->is_final = is_final;
                            frame->global_start = (int)((start+sample_offset)/seg_sample);
                            frame->global_end = frame->global_start + step/seg_sample;
                            frame->data = (float*)malloc(sizeof(float) * step);
                            memcpy(frame->data, all_samples.data()+start-offset+sample_offset, step*sizeof(float));
                            asr_online_queue.push(frame);
@@ -1200,6 +1227,8 @@
                    }else{
                        frame = new AudioFrame(0);
                        frame->is_final = true;
                        frame->global_start = speech_start;   // in this case start >= end
                        frame->global_end = speech_end_i;
                        asr_online_queue.push(frame);
                        frame = NULL;
                    }
@@ -1229,4 +1258,4 @@
    
}
} // namespace funasr
} // namespace funasr