Recherche avancée

Médias (0)

Mot : - Tags -/performance

Aucun média correspondant à vos critères n’est disponible sur le site.

Autres articles (105)

Sur d’autres sites (10689)

  • asm : FF_-prefix internal macros used in inline assembly

    25 mai 2016, par Diego Biurrun
    asm : FF_-prefix internal macros used in inline assembly
    

    These warnings conflict with system macros on Solaris, producing
    truckloads of warnings about macro redefinition.

    • [DBH] libavcodec/x86/blockdsp.c
    • [DBH] libavcodec/x86/cabac.h
    • [DBH] libavcodec/x86/fpel_mmx.c
    • [DBH] libavcodec/x86/h264_i386.h
    • [DBH] libavcodec/x86/hpeldsp_rnd_template.c
    • [DBH] libavcodec/x86/me_cmp_init.c
    • [DBH] libavcodec/x86/mpegvideo.c
    • [DBH] libavcodec/x86/mpegvideoenc_template.c
    • [DBH] libavcodec/x86/rnd_template.c
    • [DBH] libavcodec/x86/vc1dsp_mmx.c
    • [DBH] libavutil/x86/asm.h
    • [DBH] libavutil/x86/cpu.c
    • [DBH] libswscale/utils.c
    • [DBH] libswscale/x86/rgb2rgb_template.c
    • [DBH] libswscale/x86/swscale_template.c
  • H.264 muxing to MP4 from CCTV (HW) encoder using ffmpeg library in C / C++, how to fetch AVCodecContext::extradata

    26 mai 2016, par Dom

    I am trying to mux a video to mp4 file from packets received via SDK API of CCTV camera. The stream from CCTV seems to consist of packets of h264 I and P-frames only (no B-frames).

    The problem is, that the file is not playable in Daum PotPlayer when I leave the AVCodecContext::extradata empty, however, I can play the file in VLC. If I feed the extra data (probably not correctly - I just copy the first 50 bytes from the packet received from the HW encoder), the file is playable in PotPlayer, but not in VLC.

    I do not know, how to prepare the extradata properly.

    The code below shows the muxing.

    void WriteVideo()
    {
       AVFormatContext* formatContext = nullptr;
       AVStream* stream = nullptr;

       int ret = 0;

       ret = avformat_alloc_output_context2(&formatContext, nullptr, "mp4", OUTPUT_V_FILE_NAME);
       if (ret < 0)
       {
           fprintf(stderr, "Error occurred when allocating output context: %d\n", ret);
           return;
       }

       stream = avformat_new_stream(formatContext, nullptr);
       if (!stream)
       {
           avformat_free_context(formatContext);
           formatContext = nullptr;
           fprintf(stderr, "Error occurred creating new stream");
           return;
       }

       stream->codec->codec_tag = 0;

       if (formatContext->oformat->flags & AVFMT_GLOBALHEADER)
       {
           stream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
       }


       stream->codec->codec_type = AVMEDIA_TYPE_VIDEO;
       stream->codec->codec_id = AV_CODEC_ID_H264;
       stream->codec->pix_fmt = AV_PIX_FMT_YUV420P;
       stream->codec->bit_rate = 4096000; // 8192000; // 4096000; // 384000;
       stream->codec->width = 1920; // 352
       stream->codec->height = 1080; // 288
       stream->codec->gop_size = 50;

       AVRational tb;
       tb.num = 1;
       tb.den = 25;
       stream->codec->time_base = tb;
       //stream->codec->field_order = AVFieldOrder::AV_FIELD_UNKNOWN;
       //stream->codec->color_primaries = AVColorPrimaries::AVCOL_PRI_BT470BG;
       //stream->codec->color_trc = AVColorTransferCharacteristic::AVCOL_TRC_GAMMA22;
       //stream->codec->colorspace = AVColorSpace::AVCOL_SPC_BT470BG;
       //stream->codec->chroma_sample_location = AVChromaLocation::AVCHROMA_LOC_CENTER;
       AVRational aratio;
       aratio.num = 1;
       aratio.den = 1;
       stream->codec->sample_aspect_ratio = aratio;
       // stream->codec->delay = 0;
       // stream->codec->color_range = AVColorRange::AVCOL_RANGE_MPEG;

       av_dump_format(formatContext, 0, formatContext->filename, 1);

       if (!(formatContext->oformat->flags & AVFMT_NOFILE))
       {
           if (avio_open(&formatContext->pb, formatContext->filename, AVIO_FLAG_WRITE) < 0)
           {
               avformat_free_context(formatContext);
               formatContext = nullptr;
               fprintf(stderr, "Error occurred when opening output file.");
               return;

           }
       }

       avformat_write_header(formatContext, nullptr);

       int frameIdx = 0;
       int pts = 0;
       int dts = 0;
       int pkt_pos = 0;
       int size = static_cast<int>(tmpRawFrameBuffer.size());

       AVPacket pkt = { 0 };
       av_init_packet(&amp;pkt);

       while (frameIdx &lt; size)
       {
           pkt.data = tmpRawFrameBuffer[frameIdx];
           pkt.size = tmpRawFrameSizes[frameIdx];

           // debug purphose start
           FILE* f;
           char filename[MAX_PATH];
           sprintf_s(filename, MAX_PATH, OUTPUT_PACKET_FILE_PATTERN_NAME, frameIdx);
           auto err = fopen_s(&amp;f, filename, "wb");
           if (err != 0)
           {
               fprintf(stderr, "Could not open %s\n", OUTPUT_V_FILE_NAME);
               exit(1);
           }

           fflush(stdout);
           fwrite(pkt.data, 1, pkt.size, f);
           fclose(f);
           // debug purphose end

           if (tmpRawFrameTypes[frameIdx] == VIDEO_I_FRAME)
           {
               pkt.flags |= AV_PKT_FLAG_KEY;
               stream->codec->extradata_size = 50;
               stream->codec->extradata = (uint8_t*)av_malloc(stream->codec->extradata_size);
               memcpy(stream->codec->extradata, pkt.data, stream->codec->extradata_size);
           }
           pkt.pts = pts++;
           pkt.dts = dts++;
           /* rescale output packet timestamp values from codec to stream timebase */
           // av_packet_rescale_ts(&amp;pkt, stream->codec->time_base, stream->time_base);
           pkt.pts = av_rescale_q(pkt.pts, stream->codec->time_base, stream->time_base);
           pkt.dts = av_rescale_q(pkt.dts, stream->codec->time_base, stream->time_base);
           pkt.duration = 512; // should be calculated (derived from FPS 25, and 12800)
           pkt.pos = -1;
           pkt.stream_index = stream->index;

           auto ret = av_write_frame(formatContext, &amp;pkt);
           if (ret &lt; 0)
           {
               fprintf(stderr, "Error while writing video frame: %d\n", ret);
               break;
           }
           av_packet_unref(&amp;pkt);
           ++frameIdx;
       }

       if (formatContext)
       {
           av_write_trailer(formatContext);
           if (!(formatContext->oformat->flags &amp; AVFMT_NOFILE)) avio_close(formatContext->pb); // close the output file
           avformat_free_context(formatContext);
           formatContext = nullptr;
       }
    }
    </int>

    It seems, the packet from camera (buffered in tmpRawFrameBuffer vector) contains some headers, but I am not able to parse them, I do not understand the meaning of the header.

    The first bytes of the I-frame packet looks like the dump bellow :

    00 00 01 FC 02 19 F0 87 A0 23 73 41 B6 C0 01 00
    00 00 00 01 67 4D 00 2A 95 A8 1E 00 89 F9 61 00
    00 03 00 01 00 00 03 00 32 84 00 00 00 01 68 EE
    3C 80 00 00 00 01 06 E5 01 19 80 00 00 00 01 65
    B8 00 00 08 C7 B0 23 FF F7 80 EE FE 63 B6 FB F5
    ...

    The first bytes of the first P-frame :

    00 00 01 FD E5 24 00 00 00 00 00 01 61 E0 22 27
    FF D6 B0 D7 A4 2B 71 6B 19 C5 87 CA BB 8B BF 60
    14 59 B4 00 CC BC 0F C0 9E FD 84 B5 FB C4 83 DB
    5A 8B 80 FC EC D6 33 6D DE 10 96 6F 31 41 86 5C
    D4 22 F9 33 48 5B CE 77 38 17 0C D6 DD C7 6C E8
    ...

    first bytes of next P-frame :

    00 00 01 FD 5E 2F 00 00 00 00 00 01 61 E0 42 2F
    FF E7 06 DD 3C 66 26 15 94 93 7A F1 30 8A 6D B8
    AD DD 6B 0F 38 89 1D 1B 5C AC 44 6A D7 D1 21 3B
    E2 29 F8 14 BB 98 1C 06 4D B6 10 BB DB B9 CA 4F
    0B ED B1 A9 06 78 8C EC 06 6D 9F 4F 79 0C 35 5B
    ...

    ...

    begining of next I-frame :

    00 00 01 FC 02 19 F0 87 A2 23 73 41 75 89 01 00
    00 00 00 01 67 4D 00 2A 95 A8 1E 00 89 F9 61 00
    00 03 00 01 00 00 03 00 32 84 00 00 00 01 68 EE
    3C 80 00 00 00 01 06 E5 01 1B 80 00 00 00 01 65
    B8 00 00 0F 07 F0 7F F6 6C 69 43 0F F0 28 DF 97
    ...

    Does anybody know, how to fill correctly the extradata ? I just made a copy of first 50 bytes, but it seems, this is not correct.

    Probably the headers are (AUD)(SPS)(PPS)(I-Slice)(PPS)(P-Slice)(PPS)(P-Slice) ... (AUD)(SPS)(PPS)(I-Slice) (http://stackoverflow.com/a/20686267/1699328), however, I do not know, how to extract data for the

    stream->codec->extradata

    I tried to get some inspiration in this post H.264 muxed to MP4 using libavformat not playing back, but I am not able to figure out what are values of spsFrameLen, ppsFrameLen and spsFrame.

    The result of the muxer (first and last bytes of the mp4 file) :

    00 00 00 20 66 74 79 70 69 73 6F 6D 00 00 02 00
    69 73 6F 6D 69 73 6F 32 61 76 63 31 6D 70 34 31
    00 00 00 08 66 72 65 65 00 26 2E 6D 6D 64 61 74
    00 00 00 0D FC 02 19 F0 87 A0 23 73 41 B6 C0 01
    00 00 00 00 16 67 4D 00 2A 95 A8 1E 00 89 F9 61
    00 00 03 00 01 00 00 03 00 32 84 00 00 00 04 68
    EE 3C 80 00 00 00 05 06 E5 01 19 80 00 01 C0 87
    65 B8 00 00 08 C7 B0 23 FF F7 80 EE FE 63 B6 FB
    F5 97 A8 6B 48 39 61 99 FD 99 27 41 F2 78 54 EE
    D1 38 8E E8 18 DD 05 E4 BA F4 EB 69 CF 91 5C 34
    ...
    ...
    ...
    95 B8 D8 D4 C3 AF A1 BA AC 28 F0 D4 D4 7C 48 9A
    0C A6 8C 4C 98 00 00 05 1E 6D 6F 6F 76 00 00 00
    6C 6D 76 68 64 00 00 00 00 00 00 00 00 00 00 00
    00 00 00 03 E8 00 00 13 B0 00 01 00 00 01 00 00
    00 00 00 00 00 00 00 00 00 00 01 00 00 00 00 00
    00 00 00 00 00 00 00 00 00 00 01 00 00 00 00 00
    00 00 00 00 00 00 00 00 00 40 00 00 00 00 00 00
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 00 00 00 00 00 00 00 02 00 00 04 48 74 72 61
    6B 00 00 00 5C 74 6B 68 64 00 00 00 03 00 00 00
    00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 13
    B0 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 00 01 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 00 01 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 40 00 00 00 07 80 00 00 04 38 00 00 00 00 00
    24 65 64 74 73 00 00 00 1C 65 6C 73 74 00 00 00
    00 00 00 00 01 00 00 13 B0 00 00 00 00 00 01 00
    00 00 00 03 C0 6D 64 69 61 00 00 00 20 6D 64 68
    64 00 00 00 00 00 00 00 00 00 00 00 00 00 00 32
    00 00 00 FC 00 55 C4 00 00 00 00 00 2D 68 64 6C
    72 00 00 00 00 00 00 00 00 76 69 64 65 00 00 00
    00 00 00 00 00 00 00 00 00 56 69 64 65 6F 48 61
    6E 64 6C 65 72 00 00 00 03 6B 6D 69 6E 66 00 00
    00 14 76 6D 68 64 00 00 00 01 00 00 00 00 00 00
    00 00 00 00 00 24 64 69 6E 66 00 00 00 1C 64 72
    65 66 00 00 00 00 00 00 00 01 00 00 00 0C 75 72
    6C 20 00 00 00 01 00 00 03 2B 73 74 62 6C 00 00
    00 93 73 74 73 64 00 00 00 00 00 00 00 01 00 00
    00 83 61 76 63 31 00 00 00 00 00 00 00 01 00 00
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 07 80
    04 38 00 48 00 00 00 48 00 00 00 00 00 00 00 01
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
    00 18 FF FF 00 00 00 2D 61 76 63 43 01 4D 00 2A
    FF E1 00 16 67 4D 00 2A 95 A8 1E 00 89 F9 61 00
    00 03 00 01 00 00 03 00 32 84 01 00 04 68 EE 3C
    80 00 00 00 18 73 74 74 73 00 00 00 00 00 00 00
    01 00 00 00 7E 00 00 02 00 00 00 00 1C 73 74 73
    73 00 00 00 00 00 00 00 03 00 00 00 01 00 00 00
    33 00 00 00 65 00 00 00 34 73 74 73 63 00 00 00
    00 00 00 00 03 00 00 00 01 00 00 00 3B 00 00 00
    01 00 00 00 02 00 00 00 37 00 00 00 01 00 00 00
    03 00 00 00 0C 00 00 00 01 00 00 02 0C 73 74 73
    7A 00 00 00 00 00 00 00 00 00 00 00 7E 00 01 C0
    C7 00 00 24 EE 00 00 2F 67 00 00 1D 83 00 00 2E
    8F 00 00 30 B6 00 00 2F 44 00 00 2F 50 00 00 34
    6B 00 00 30 BE 00 00 31 0C 00 00 31 E7 00 00 30
    EA 00 00 31 4E 00 00 31 A8 00 00 32 21 00 00 31
    E6 00 00 31 B5 00 00 31 14 00 00 31 AF 00 00 31
    9D 00 00 33 60 00 00 32 11 00 00 32 4C 00 00 31
    F0 00 00 32 91 00 00 43 43 00 00 44 29 00 00 44
    EC 00 00 44 20 00 00 44 86 00 00 45 AD 00 00 47
    47 00 00 46 9F 00 00 46 D9 00 00 47 BE 00 00 48
    CD 00 00 3E 50 00 00 40 98 00 00 41 0E 00 00 40
    43 00 00 41 07 00 00 41 BB 00 00 41 FF 00 00 30
    5E 00 00 33 C7 00 00 34 B7 00 00 33 F1 00 00 33
    0D 00 00 32 DB 00 01 89 86 00 00 3B E1 00 00 3C
    55 00 00 3C 64 00 00 3C B7 00 00 3C FD 00 00 3E
    54 00 00 3E C5 00 00 3E 1C 00 00 3E 94 00 00 3E
    44 00 00 3E D7 00 00 3F CC 00 00 3E D6 00 00 40
    00 00 00 40 4D 00 00 40 04 00 00 3F A9 00 00 40
    82 00 00 41 0F 00 00 41 64 00 00 41 E5 00 00 42
    1E 00 00 42 2C 00 00 42 80 00 00 42 4D 00 00 43
    9F 00 00 43 DA 00 00 44 45 00 00 44 21 00 00 44
    B7 00 00 45 22 00 00 45 E3 00 00 45 BF 00 00 46
    18 00 00 47 4B 00 00 45 05 00 00 47 34 00 00 46
    60 00 00 46 97 00 00 46 66 00 00 46 29 00 00 46
    38 00 00 47 1D 00 00 47 42 00 00 47 18 00 00 47
    13 00 00 46 52 00 00 47 48 00 00 46 F8 00 01 BE
    E3 00 00 3F 56 00 00 3B 32 00 00 38 F8 00 00 37
    56 00 00 36 2D 00 00 35 DA 00 00 34 6B 00 00 3E
    BE 00 00 3E B5 00 00 3F 33 00 00 3F AC 00 00 3F
    38 00 00 42 32 00 01 1B DC 00 01 80 50 00 01 14
    06 00 00 C2 BB 00 00 96 12 00 00 6D EC 00 00 54
    E6 00 00 3A AC 00 00 32 00 00 00 2F 0A 00 00 2D
    F1 00 00 1B 7F 00 00 00 1C 73 74 63 6F 00 00 00
    00 00 00 00 03 00 00 00 30 00 0F DD AB 00 1F 7D
    9E 00 00 00 62 75 64 74 61 00 00 00 5A 6D 65 74
    61 00 00 00 00 00 00 00 21 68 64 6C 72 00 00 00
    00 00 00 00 00 6D 64 69 72 61 70 70 6C 00 00 00
    00 00 00 00 00 00 00 00 00 2D 69 6C 73 74 00 00
    00 25 A9 74 6F 6F 00 00 00 1D 64 61 74 61 00 00
    00 01 00 00 00 00 4C 61 76 66 35 37 2E 32 33 2E
    31 30 30

    Thanks a lot for any advices.

  • How to resample an audio with ffmpeg API ?

    13 mai 2016, par tangren

    I’d like to decode audio file(.wav .aac etc.) into raw data(pcm) and then resample it with ffmpeg API.

    I try to do it with the help of the official examples. However, the result file always loses a little data at the end of the file compared to the file generated by ffmpeg command :

    ffmpeg -i audio.wav -f s16le -ac 1 -ar 8000 -acodec pcm_s16le out.pcm.

    In this case, the input audio metadata : pcm_s16le, 16000 Hz, 1 channels, s16, 256 kb/s

    And there are 32 bites lost at the end of result file.

    What’s more, I’d like to process audios in memory, so how do I calculate the size of audio’s raw data (pcm) ?

    My code :

    #include <libavutil></libavutil>opt.h>
    #include <libavutil></libavutil>imgutils.h>
    #include <libavutil></libavutil>samplefmt.h>
    #include <libavutil></libavutil>timestamp.h>
    #include <libavformat></libavformat>avformat.h>
    #include <libavutil></libavutil>channel_layout.h>
    #include <libswresample></libswresample>swresample.h>

    int convert_to_PCM(const char* src_audio_filename, const char* dst_pcm_filename, int dst_sample_rate)
    {
       FILE *audio_dst_file = NULL;

       // for demuxing and decoding
       int ret = 0, got_frame, decoded, tmp;
       AVFormatContext *fmt_ctx = NULL;
       AVCodecContext *audio_dec_ctx;
       AVStream *audio_stream = NULL;
       int audio_stream_idx = -1;
       AVFrame *frame = NULL;
       AVPacket pkt;

       // for resampling
       struct SwrContext *swr_ctx = NULL;
       int src_sample_rate;
       uint8_t **dst_data = NULL;
       int dst_nb_samples, max_dst_nb_samples;
       enum AVSampleFormat src_sample_fmt, dst_sample_fmt = AV_SAMPLE_FMT_S16;
       int nb_channels = 1;
       int dst_bufsize, dst_linesize;
       int64_t src_ch_layout, dst_ch_layout;
       dst_ch_layout = src_ch_layout = av_get_default_channel_layout(1);

       av_register_all();

       if (avformat_open_input(&amp;fmt_ctx, src_audio_filename, NULL, NULL) &lt; 0) {
           fprintf(stderr, "Could not open source file %s\n", src_audio_filename);
           return 1;
       }

       /* retrieve stream information */
       if (avformat_find_stream_info(fmt_ctx, NULL) &lt; 0) {
           fprintf(stderr, "Could not find stream information\n");
           return 1;
       }

       if (open_codec_context(&amp;audio_stream_idx, fmt_ctx, AVMEDIA_TYPE_AUDIO) >= 0) {
           audio_stream = fmt_ctx->streams[audio_stream_idx];
           audio_dec_ctx = audio_stream->codec;
           audio_dst_file = fopen(dst_pcm_filename, "wb");
           if (!audio_dst_file) {
               fprintf(stderr, "Could not open destination file %s\n", dst_pcm_filename);
               ret = 1;
               goto end;
           }
       }

       /* dump input information to stderr */
       av_dump_format(fmt_ctx, 0, src_audio_filename, 0);

       if (!audio_stream) {
           fprintf(stderr, "Could not find audio stream in the input, aborting\n");
           ret = 1;
           goto end;
       }

       src_sample_rate = audio_dec_ctx->sample_rate;
       if (src_sample_rate != dst_sample_rate) {
           /* create resampler context */
           swr_ctx = swr_alloc();
           if (!swr_ctx) {
               fprintf(stderr, "Could not allocate resampler context\n");
               ret = AVERROR(ENOMEM);
               goto end;
           }
           src_sample_fmt = audio_dec_ctx->sample_fmt;


           /* set options */
           av_opt_set_int(swr_ctx, "in_channel_layout",    src_ch_layout, 0);
           av_opt_set_int(swr_ctx, "in_sample_rate",       src_sample_rate, 0);
           av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0);

           av_opt_set_int(swr_ctx, "out_channel_layout",    dst_ch_layout, 0);
           av_opt_set_int(swr_ctx, "out_sample_rate",       dst_sample_rate, 0);
           av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", dst_sample_fmt, 0);

           /* initialize the resampling context */
           if ((ret = swr_init(swr_ctx)) &lt; 0) {
               fprintf(stderr, "Failed to initialize the resampling context\n");
               goto end;
           }

       }

       frame = av_frame_alloc();
       if (!frame) {
           fprintf(stderr, "Could not allocate frame\n");
           ret = AVERROR(ENOMEM);
           goto end;
       }

       /* initialize packet, set data to NULL, let the demuxer fill it */
       av_init_packet(&amp;pkt);
       pkt.data = NULL;
       pkt.size = 0;

       printf("Convert audio from file '%s' into '%s'\n", src_audio_filename, dst_pcm_filename);

       /* read frames from the file */
       while (av_read_frame(fmt_ctx, &amp;pkt) >= 0) {
           AVPacket orig_pkt = pkt;
           do {
               decoded = pkt.size;
               got_frame = 0;
               tmp = 0;
               /* decode audio frame */
               tmp = avcodec_decode_audio4(audio_dec_ctx, frame, &amp;got_frame, &amp;pkt);
               if (tmp &lt; 0) {
                   fprintf(stderr, "Error decoding audio frame (%s)\n", av_err2str(tmp));
                   break;
               }
               decoded = FFMIN(tmp, pkt.size);
               if (got_frame) {
                   if (swr_ctx) {
                       if (dst_data == NULL) {
                           max_dst_nb_samples = dst_nb_samples = av_rescale_rnd(frame->nb_samples, dst_sample_rate, src_sample_rate, AV_ROUND_UP);
                           ret = av_samples_alloc_array_and_samples(&amp;dst_data, &amp;dst_linesize, nb_channels,
                                                                   dst_nb_samples, dst_sample_fmt, 0);
                           if (ret &lt; 0) {
                               fprintf(stderr, "Could not allocate destination samples\n");
                               goto end;
                           }
                       }
                       dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, src_sample_rate) + frame->nb_samples, dst_sample_rate, src_sample_rate, AV_ROUND_UP);
                       if (dst_nb_samples > max_dst_nb_samples) {
                           av_freep(&amp;dst_data[0]);
                           ret = av_samples_alloc(dst_data, &amp;dst_linesize, nb_channels, dst_nb_samples, dst_sample_fmt, 1);
                           if (ret &lt; 0)
                               break;
                           max_dst_nb_samples = dst_nb_samples;
                       }

                       /* convert to destination format */
                       ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t **)frame->data, frame->nb_samples);
                       if (ret &lt; 0) {
                           fprintf(stderr, "Error while converting\n");
                           goto end;
                       }
                       dst_bufsize = av_samples_get_buffer_size(&amp;dst_linesize, nb_channels, ret, dst_sample_fmt, 1);
                       if (dst_bufsize &lt; 0) {
                           fprintf(stderr, "Could not get sample buffer size\n");
                           goto end;
                       }
                       printf("Decoded size: %d, dst_nb_samples: %d, converted size: %d, sample buffer size: %d\n", decoded, dst_nb_samples, ret, dst_bufsize);
                       fwrite(dst_data[0], 1, dst_bufsize, audio_dst_file);
                   }
                   else {
                       size_t unpadded_linesize = frame->nb_samples * av_get_bytes_per_sample(frame->format);
                       fwrite(frame->extended_data[0], 1, unpadded_linesize, audio_dst_file);
                   }
               }

               if (decoded &lt; 0)
                   break;
               pkt.data += tmp;
               pkt.size -= tmp;
           } while (pkt.size > 0);
           av_packet_unref(&amp;orig_pkt);
       }

       printf("Convert succeeded.\n");

    end:
       avcodec_close(audio_dec_ctx);
       avformat_close_input(&amp;fmt_ctx);
       if (audio_dst_file)
           fclose(audio_dst_file);
       av_frame_free(&amp;frame);
       if (dst_data)
           av_freep(&amp;dst_data[0]);
       av_freep(&amp;dst_data);
       swr_free(&amp;swr_ctx);

       return ret;
    }

    static int open_codec_context(int *stream_idx,
                               AVFormatContext *fmt_ctx, enum AVMediaType type)
    {
       int ret, stream_index;
       AVStream *st;
       AVCodecContext *dec_ctx = NULL;
       AVCodec *dec = NULL;
       AVDictionary *opts = NULL;

       ret = av_find_best_stream(fmt_ctx, type, -1, -1, NULL, 0);
       if (ret &lt; 0) {
           fprintf(stderr, "Could not find %s stream in input file.\n",
                   av_get_media_type_string(type));
           return ret;
       } else {
           stream_index = ret;
           st = fmt_ctx->streams[stream_index];

           /* find decoder for the stream */
           dec_ctx = st->codec;
           dec = avcodec_find_decoder(dec_ctx->codec_id);
           if (!dec) {
               fprintf(stderr, "Failed to find %s codec\n",
                       av_get_media_type_string(type));
               return AVERROR(EINVAL);
           }

           if ((ret = avcodec_open2(dec_ctx, dec, &amp;opts)) &lt; 0) {
               fprintf(stderr, "Failed to open %s codec\n",
                       av_get_media_type_string(type));
               return ret;
           }
           *stream_idx = stream_index;
       }

       return 0;
    }

    static int get_format_from_sample_fmt(const char **fmt,
                                       enum AVSampleFormat sample_fmt)
    {
       int i;
       struct sample_fmt_entry {
           enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le;
       } sample_fmt_entries[] = {
           { AV_SAMPLE_FMT_U8,  "u8",    "u8"    },
           { AV_SAMPLE_FMT_S16, "s16be", "s16le" },
           { AV_SAMPLE_FMT_S32, "s32be", "s32le" },
           { AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
           { AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
       };
       *fmt = NULL;

       for (i = 0; i &lt; FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
           struct sample_fmt_entry *entry = &amp;sample_fmt_entries[i];
           if (sample_fmt == entry->sample_fmt) {
               *fmt = AV_NE(entry->fmt_be, entry->fmt_le);
               return 0;
           }
       }

       fprintf(stderr,
               "sample format %s is not supported as output format\n",
               av_get_sample_fmt_name(sample_fmt));
       return -1;
    }