我想用FFmpeg和libao写一个程序来读取和播放一个音频文件。我一直在按照在 FFmpeg文件 用来解码音频,使用新的 avcodec_send_packet
和 avcodec_receive_frame
函数,但我能找到的例子却很少(FFmpeg文档中的例子要么没有使用libavformat,要么使用了被废弃的 avcodec_decode_audio4
). 我的很多程序都是基于 转码_aac.c 例子(最多 init_resampler
),但它也使用了被废弃的解码功能。
我相信我已经把程序的解码部分工作好了,但是我需要对音频进行重新采样,以便把它转换成交错格式发送给libao,为此我试图使用libswresample。每当程序在当前状态下运行时,它都会输出(多次)"Error resampling: 输出改变了"。我一直使用的测试文件只是我手头的YouTube翻录,ffprobe报告唯一的流为。
Stream #0:0(und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 125 kb/s (default)
这是我第一个使用FFmpeg的程序(我对C语言还比较陌生) 所以欢迎大家给我任何关于如何改进和修复程序其他部分的建议。
#include<stdio.h>
#include<libavcodec/avcodec.h>
#include<libavformat/avformat.h>
#include<libavutil/avutil.h>
#include<libswresample/swresample.h>
#include<ao/ao.h>
#define OUTPUT_CHANNELS 2
#define OUTPUT_RATE 44100
#define BUFFER_SIZE 192000
#define OUTPUT_BITS 16
#define OUTPUT_FMT AV_SAMPLE_FMT_S16
static char *errtext (int err) {
static char errbuff[256];
av_strerror(err,errbuff,sizeof(errbuff));
return errbuff;
}
static int open_audio_file (const char *filename, AVFormatContext **context, AVCodecContext **codec_context) {
AVCodecContext *avctx;
AVCodec *codec;
int ret;
int stream_id;
int i;
// Open input file
if ((ret = avformat_open_input(context,filename,NULL,NULL)) < 0) {
fprintf(stderr,"Error opening input file '%s': %s\n",filename,errtext(ret));
*context = NULL;
return ret;
}
// Get stream info
if ((ret = avformat_find_stream_info(*context,NULL)) < 0) {
fprintf(stderr,"Unable to find stream info: %s\n",errtext(ret));
avformat_close_input(context);
return ret;
}
// Find the best stream
if ((stream_id = av_find_best_stream(*context,AVMEDIA_TYPE_AUDIO,-1,-1,&codec,0)) < 0) {
fprintf(stderr,"Unable to find valid audio stream: %s\n",errtext(stream_id));
avformat_close_input(context);
return stream_id;
}
// Allocate a decoding context
if (!(avctx = avcodec_alloc_context3(codec))) {
fprintf(stderr,"Unable to allocate decoder context\n");
avformat_close_input(context);
return AVERROR(ENOMEM);
}
// Initialize stream parameters
if ((ret = avcodec_parameters_to_context(avctx,(*context)->streams[stream_id]->codecpar)) < 0) {
fprintf(stderr,"Unable to get stream parameters: %s\n",errtext(ret));
avformat_close_input(context);
avcodec_free_context(&avctx);
return ret;
}
// Open the decoder
if ((ret = avcodec_open2(avctx,codec,NULL)) < 0) {
fprintf(stderr,"Could not open codec: %s\n",errtext(ret));
avformat_close_input(context);
avcodec_free_context(&avctx);
return ret;
}
*codec_context = avctx;
return 0;
}
static void init_packet (AVPacket *packet) {
av_init_packet(packet);
packet->data = NULL;
packet->size = 0;
}
static int init_resampler (AVCodecContext *codec_context, SwrContext **resample_context) {
int ret;
// Set resampler options
*resample_context = swr_alloc_set_opts(NULL,
av_get_default_channel_layout(OUTPUT_CHANNELS),
OUTPUT_FMT,
codec_context->sample_rate,
av_get_default_channel_layout(codec_context->channels),
codec_context->sample_fmt,
codec_context->sample_rate,
0,NULL);
if (!(*resample_context)) {
fprintf(stderr,"Unable to allocate resampler context\n");
return AVERROR(ENOMEM);
}
// Open the resampler
if ((ret = swr_init(*resample_context)) < 0) {
fprintf(stderr,"Unable to open resampler context: %s\n",errtext(ret));
swr_free(resample_context);
return ret;
}
return 0;
}
static int init_frame (AVFrame **frame) {
if (!(*frame = av_frame_alloc())) {
fprintf(stderr,"Could not allocate frame\n");
return AVERROR(ENOMEM);
}
return 0;
}
int main (int argc, char *argv[]) {
AVFormatContext *context = 0;
AVCodecContext *codec_context;
SwrContext *resample_context = NULL;
AVPacket packet;
AVFrame *frame = 0;
AVFrame *resampled = 0;
int16_t *buffer;
int ret, packet_ret, finished;
ao_device *device;
ao_sample_format format;
int default_driver;
if (argc != 2) {
fprintf(stderr,"Usage: %s <filename>\n",argv[0]);
return 1;
}
av_register_all();
printf("Opening file...\n");
if (open_audio_file(argv[1],&context,&codec_context) < 0)
return 1;
printf("Initializing resampler...\n");
if (init_resampler(codec_context,&resample_context) < 0) {
avformat_close_input(&context);
avcodec_free_context(&codec_context);
return 1;
}
// Setup libao
printf("Starting audio device...\n");
ao_initialize();
default_driver = ao_default_driver_id();
format.bits = OUTPUT_BITS;
format.channels = OUTPUT_CHANNELS;
format.rate = codec_context->sample_rate;
format.byte_format = AO_FMT_NATIVE;
format.matrix = 0;
if ((device = ao_open_live(default_driver,&format,NULL)) == NULL) {
fprintf(stderr,"Error opening audio device\n");
avformat_close_input(&context);
avcodec_free_context(&codec_context);
swr_free(&resample_context);
return 1;
}
// Mainloop
printf("Beginning mainloop...\n");
init_packet(&packet);
// Read packets until done
while (1) {
packet_ret = av_read_frame(context,&packet);
// Send a packet
if ((ret = avcodec_send_packet(codec_context,&packet)) < 0)
fprintf(stderr,"Error sending packet to decoder: %s\n",errtext(ret));
av_packet_unref(&packet);
while (1) {
if (!frame)
frame = av_frame_alloc();
ret = avcodec_receive_frame(codec_context,frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) // Need more input
break;
else if (ret < 0) {
fprintf(stderr,"Error receiving frame: %s\n",errtext(ret));
break;
}
// We have a valid frame, need to resample it
if (!resampled)
resampled = av_frame_alloc();
resampled->channel_layout = av_get_default_channel_layout(OUTPUT_CHANNELS);
resampled->sample_rate = codec_context->sample_rate;
resampled->format = OUTPUT_FMT;
if ((ret = swr_convert_frame(resample_context,resampled,frame)) < 0) {
fprintf(stderr,"Error resampling: %s\n",errtext(ret));
} else {
ao_play(device,(char*)resampled->extended_data[0],resampled->linesize[0]);
}
av_frame_unref(resampled);
av_frame_unref(frame);
}
if (packet_ret == AVERROR_EOF)
break;
}
printf("Closing file and freeing contexts...\n");
avformat_close_input(&context);
avcodec_free_context(&codec_context);
swr_free(&resample_context);
printf("Closing audio device...\n");
ao_close(device);
ao_shutdown();
return 0;
}
更新。 我已经得到了它播放的声音,但它听起来像样品丢失(和MP3文件警告说:"无法更新时间戳为跳过的样品")。问题是 resampled
框架需要在传递给 swr_convert_frame
. 我还加了 av_packet_unref
和 av_frame_unref
但我仍然不知道在哪里可以找到它们。
ao_play(device,(char*)resampled->extended_data[0],resampled->linesize[0]);
这一行有问题。swr_convert_frame将数据和extended_data字段与沉默对齐。swr_convert_frame将数据和extended_data字段与静默字段对齐,这个静默字段包含在lineize参数中,所以你将错误的帧大小传递给ao_play函数。
ao_play(device, (char*)resampled->extended_data[0], av_sample_get_buffer_size(resampled->linesize, resampled->channels, resampled->nb_samples, resampled->format, 0));
函数av_sample_get_buffer_size()返回真实的样本大小,不需要对齐。当我遇到类似的问题时,这就是解决方案。