Recherche avancée

Sur d’autres sites (6170)

• python multiprocessing and ffmpeg corrupts files

  1er juillet 2012, par misterte

  I'm currently trying to convert several videos to three different outputs, all using ffmpeg : mp4, webm and jpeg. I also need to run this script in different directories and create within the directories webm, mp4 and jpeg subdirectories where the respective converted files are stored.

  I am running the following script inside a directory with 8 .mov test files in it. Files work ok as .mov.

  (It's a bit long, so here you can view it online)

  The script creates all files and directories. I can also note that all Consumer processes take tasks and complete them. The problem is resulting .mp4 and .webm files are corrupted.

  Here you can see an example output. It's a bit long, so I think it's best if I point out the part I think is relevant.

  ...
  
  [h264 @ 0x121815a00]no frame!
  
  Error while decoding stream #0.0
  
  [h264 @ 0x121815a00]AVC: nal size -6554108
  
  [h264 @ 0x121815a00]no frame!
  
  Error while decoding stream #0.0
  
  [h264 @ 0x121815a00]AVC: nal size 391580264
  
  [h264 @ 0x121815a00]no frame!
  
  ...

  This does not happen if I run ffmpeg straight from the console.

  ffmpeg -i movie.mov -b 500k -s 640x360 -padtop 60 -padbottom 60 movie_out.webm

  I can even run it in parallel shells and the output will not be affected.

  Can anyone see what the problem is ?

  thnx !

  A.

• FFmpeg/libav : YUV420P to RGB conversion

  17 janvier 2014, par learner

  I am working with Video encoding-decoding based on online tutorials. In the encoding section, the dummy image created is in YUV420P format. I need it to be in RGB or BGR format. Any idea how to do this ??

   #include 
  
   #include 
  
   #include 
  
  
  
   #ifdef HAVE_AV_CONFIG_H
  
   #undef HAVE_AV_CONFIG_H
  
   #endif
  
  
  
   #include "libavcodec/avcodec.h"
  
   #include "libavutil/mathematics.h"
  
  
  
   #define INBUF_SIZE 4096
  
   #define AUDIO_INBUF_SIZE 20480
  
   #define AUDIO_REFILL_THRESH 4096
  
  
  
   /*
  
   * Video encoding example
  
   */
  
   static void video_encode_example(const char *filename)
  
   {
  
       AVCodec *codec;
  
       AVCodecContext *c = NULL;
  
       int i, out_size, size, x, y, outbuf_size;
  
       FILE *f;
  
       AVFrame *picture;
  
       uint8_t *outbuf, *picture_buf;
  
  
  
       printf("Video encoding\n");
  
  
  
       /* find the mpeg1 video encoder */
  
       codec = avcodec_find_encoder(CODEC_ID_MPEG1VIDEO);
  
       if (!codec)
  
       {
  
           fprintf(stderr, "codec not found\n");
  
           exit(1);
  
       }
  
  
  
       c = avcodec_alloc_context();
  
       picture = avcodec_alloc_frame();
  
  
  
       /* put sample parameters */
  
       c->bit_rate = 400000;
  
       /* resolution must be a multiple of two */
  
       c->width = 352;
  
       c->height = 288;
  
       /* frames per second */
  
       c->time_base= (AVRational){1,25};
  
       c->gop_size = 10; /* emit one intra frame every ten frames */
  
       c->max_b_frames=1;
  
       c->pix_fmt = PIX_FMT_YUV420P;
  
  
  
       /* open it */
  
       if (avcodec_open(c, codec) < 0)
  
       {
  
           fprintf(stderr, "could not open codec\n");
  
           exit(1);
  
       }
  
  
  
       f = fopen(filename, "wb");
  
       if (!f)
  
       {
  
           fprintf(stderr, "could not open file! %s\n", filename);
  
           exit(1);
  
       }
  
  
  
       /* alloc image and output buffer */
  
       outbuf_size = 100000;
  
       outbuf = malloc(outbuf_size);
  
       size = c->width * c->height;
  
       picture_buf = malloc((size * 3) / 2); /* size for YUV 420 */
  
  
  
       picture->data[0] = picture_buf;
  
       picture->data[1] = picture->data[0] + size;
  
       picture->data[2] = picture->data[1] + size / 4;
  
       picture->linesize[0] = c->width;
  
       picture->linesize[1] = c->width / 2;
  
       picture->linesize[2] = c->width / 2;
  
  
  
       /* encode 1 second of video */
  
       for(i=0; i<25; i++)
  
       {
  
           fflush(stdout);
  
           /* prepare a dummy image */
  
           /* Y */
  
           for(y=0; y < c->height; y++)
  
           {
  
               for(x=0; x < c->width; x++)
  
               {
  
                   picture->data[0][y * picture->linesize[0] + x] = x + y + i * 3;
  
               }
  
           }
  
  
  
           /* Cb and Cr */
  
           for(y=0; y < c->height/2; y++)
  
           {
  
               for(x=0; x < c->width/2; x++)
  
               {
  
                   picture->data[1][y * picture->linesize[1] + x] = 128 + y + i * 2;
  
                   picture->data[2][y * picture->linesize[2] + x] = 64 + x + i * 5;
  
               }
  
           }
  
  
  
           /* encode the image */
  
           out_size = avcodec_encode_video(c, outbuf, outbuf_size, picture);
  
           printf("encoding frame %3d (size=%5d)\n", i, out_size);
  
           fwrite(outbuf, 1, out_size, f);
  
       }
  
  
  
       /* get the delayed frames */
  
       for(; out_size; i++)
  
       {
  
           fflush(stdout);
  
  
  
           out_size = avcodec_encode_video(c, outbuf, outbuf_size, NULL);
  
           printf("write frame %3d (size=%5d)\n", i, out_size);
  
           fwrite(outbuf, 1, out_size, f);
  
       }
  
  
  
       /* add sequence end code to have a real mpeg file */
  
       outbuf[0] = 0x00;
  
       outbuf[1] = 0x00;
  
       outbuf[2] = 0x01;
  
       outbuf[3] = 0xb7;
  
       fwrite(outbuf, 1, 4, f);
  
       fclose(f);
  
       free(picture_buf);
  
       free(outbuf);
  
  
  
       avcodec_close(c);
  
       av_free(c);
  
       av_free(picture);
  
       printf("\n");
  
   }
  
  
  
   /*
  
    * Video decoding example
  
    */
  
  
  
   static void pgm_save(unsigned char *buf, int wrap, int xsize, int ysize,
  
                        char *filename)
  
   {
  
       FILE *f;
  
       int i;
  
  
  
       f=fopen(filename,"w");
  
       fprintf(f,"P5\n%d %d\n%d\n",xsize,ysize,255);
  
       for(i=0; i* set end of buffer to 0 (this ensures that no overreading happens for damaged mpeg streams) */
  
       memset(inbuf + INBUF_SIZE, 0, FF_INPUT_BUFFER_PADDING_SIZE);
  
  
  
       printf("Video decoding\n");
  
  
  
       /* find the mpeg1 video decoder */
  
       codec = avcodec_find_decoder(CODEC_ID_MPEG1VIDEO);
  
       if (!codec) {
  
           fprintf(stderr, "codec not found\n");
  
           exit(1);
  
       }
  
  
  
       c = avcodec_alloc_context();
  
       picture = avcodec_alloc_frame();
  
  
  
       if(codec->capabilities&CODEC_CAP_TRUNCATED)
  
           c->flags|= CODEC_FLAG_TRUNCATED; /* we do not send complete frames */
  
  
  
       /* For some codecs, such as msmpeg4 and mpeg4, width and height
  
          MUST be initialized there because this information is not
  
          available in the bitstream. */
  
  
  
       /* open it */
  
       if (avcodec_open(c, codec) < 0) {
  
           fprintf(stderr, "could not open codec\n");
  
           exit(1);
  
       }
  
  
  
       /* the codec gives us the frame size, in samples */
  
  
  
       f = fopen(filename, "rb");
  
       if (!f) {
  
           fprintf(stderr, "could not open file! %s\n", filename);
  
           exit(1);
  
       }
  
  
  
       frame = 0;
  
       for(;;) {
  
           avpkt.size = fread(inbuf, 1, INBUF_SIZE, f);
  
           if (avpkt.size == 0)
  
               break;
  
  
  
           /* NOTE1: some codecs are stream based (mpegvideo, mpegaudio)
  
              and this is the only method to use them because you cannot
  
              know the compressed data size before analysing it.
  
  
  
              BUT some other codecs (msmpeg4, mpeg4) are inherently frame
  
              based, so you must call them with all the data for one
  
              frame exactly. You must also initialize 'width' and
  
              'height' before initializing them. */
  
  
  
           /* NOTE2: some codecs allow the raw parameters (frame size,
  
              sample rate) to be changed at any frame. We handle this, so
  
              you should also take care of it */
  
  
  
           /* here, we use a stream based decoder (mpeg1video), so we
  
              feed decoder and see if it could decode a frame */
  
  
  
           avpkt.data = inbuf;
  
           while (avpkt.size > 0)
  
           {
  
               len = avcodec_decode_video2(c, picture, &got_picture, &avpkt);
  
               if (len < 0)
  
               {
  
                   fprintf(stderr, "Error while decoding frame %d\n", frame);
  
                   exit(1);
  
               }
  
               if (got_picture)
  
               {
  
                   printf("saving frame %3d\n", frame);
  
                   fflush(stdout);
  
  
  
                   /* the picture is allocated by the decoder. no need to
  
                      free it */
  
                   snprintf(buf, sizeof(buf), outfilename, frame);
  
                   pgm_save(picture->data[0], picture->linesize[0],
  
                            c->width, c->height, buf);
  
                   frame++;
  
               }
  
               avpkt.size -= len;
  
               avpkt.data += len;
  
           }
  
       }
  
  
  
       /* some codecs, such as MPEG, transmit the I and P frame with a
  
          latency of one frame. You must do the following to have a
  
          chance to get the last frame of the video */
  
  
  
       avpkt.data = NULL;
  
       avpkt.size = 0;
  
       len = avcodec_decode_video2(c, picture, &got_picture, &avpkt);
  
       if (got_picture)
  
       {
  
           printf("saving last frame %3d\n", frame);
  
           fflush(stdout);
  
  
  
           /* the picture is allocated by the decoder. no need to
  
              free it */
  
           snprintf(buf, sizeof(buf), outfilename, frame);
  
           pgm_save(picture->data[0], picture->linesize[0],
  
                    c->width, c->height, buf);
  
           frame++;
  
       }
  
  
  
       fclose(f);
  
  
  
       avcodec_close(c);
  
       av_free(c);
  
       av_free(picture);
  
       printf("\n");
  
   }
  
  
  
   int main(int argc, char **argv)
  
   {
  
       const char *filename;
  
  
  
       /* must be called before using avcodec lib */
  
       avcodec_init();
  
  
  
       /* register all the codecs */
  
       avcodec_register_all();
  
  
  
       if (argc <= 1)
  
       { 
  
           video_encode_example("asdf.mpg");
  
           filename = "asdf.mpg";
  
       }
  
       else
  
       {
  
           filename = argv[1];
  
       }
  
  
  
       video_decode_example("%d.pgm", filename);
  
  
  
       return 0;
  
  }

  I tried with PIX_FMT_RGB24 and changing each channel accordingly. For this, I declared another :

  AVFrame *pictureRGB ; and then : pictureRGB = avcodec_alloc_frame() ;

  for(y=0; y < c->height; y++)
  
  {
  
       for(x=0; x < c->width; x++)
  
       {
  
            pictureRGB ->data[0][y * pictureRGB ->linesize[0] + x] = x + y + i * 3;
  
            pictureRGB ->data[1][y * pictureRGB ->linesize[1] + x] = x + y + i * 3;
  
            pictureRGB ->data[2][y * pictureRGB ->linesize[2] + x] = x + y + i * 3;
  
       }
  
  }

  But it gives errors ! I am totally new to this library. Is it possible to directly encode as a RGB dummy image rather than as YUV420P. Anybody out there with sound knowledge in this area ??? Thanks in advance !

• FFmpeg library : webm (vorbis) audio to aac conversion

  3 janvier 2014, par taansari

  I have written a small program to convert webm (vorbis) audio to aac format, using FFmpeg libraries - C++ (on Windows using 32 bit Zeranoe FFmpeg builds). After writing this program, I find it is sometimes converting files as per expectation, and at other times, results in larger duration files, and audio playback is broken/awkward as well.

  This code appears to be working fine for mp3, which also uses FLTP format (same as vorbis), so technically both look similar.

  Please see below sample code I am using :

  ////////////////////////////////////////////////
  
  #include "stdafx.h"
  
  
  
  #include <iostream>
  
  #include <fstream>
  
  
  
  #include <string>
  
  #include <vector>
  
  #include <map>
  
  
  
  #include <deque>
  
  #include <queue>
  
  
  
  #include 
  
  #include 
  
  #include 
  
  #include 
  
  
  
  extern "C"
  
  {
  
  #include "libavcodec/avcodec.h"
  
  #include "libavformat/avformat.h"
  
  #include "libavdevice/avdevice.h"
  
  #include "libswscale/swscale.h"
  
  #include "libavutil/dict.h"
  
  #include "libavutil/error.h"
  
  #include "libavutil/opt.h"
  
  #include <libavutil></libavutil>fifo.h>
  
  #include <libavutil></libavutil>imgutils.h>
  
  #include <libavutil></libavutil>samplefmt.h>
  
  #include <libswresample></libswresample>swresample.h>
  
  }
  
  
  
  AVFormatContext*    fmt_ctx= NULL;
  
  int                    audio_stream_index = -1;
  
  AVCodecContext *    codec_ctx_audio = NULL;
  
  AVCodec*            codec_audio = NULL;
  
  AVFrame*            decoded_frame = NULL;
  
  uint8_t**            audio_dst_data = NULL;
  
  int                    got_frame = 0;
  
  int                    audiobufsize = 0;
  
  AVPacket            input_packet;
  
  int                    audio_dst_linesize = 0;
  
  int                    audio_dst_bufsize = 0;
  
  SwrContext *        swr = NULL;
  
  
  
  AVOutputFormat *    output_format = NULL ;
  
  AVFormatContext *    output_fmt_ctx= NULL;
  
  AVStream *            audio_st = NULL;
  
  AVCodec *            audio_codec = NULL;
  
  double                audio_pts = 0.0;
  
  AVFrame *            out_frame = avcodec_alloc_frame();
  
  
  
  int                    audio_input_frame_size = 0;
  
  
  
  uint8_t *            audio_data_buf = NULL;
  
  uint8_t *            audio_out = NULL;
  
  int                    audio_bit_rate;
  
  int                    audio_sample_rate;
  
  int                    audio_channels;
  
  
  
  int decode_packet();
  
  int open_audio_input(char* src_filename);
  
  int decode_frame();
  
  
  
  int open_encoder(char* output_filename);
  
  AVStream *add_audio_stream(AVFormatContext *oc, AVCodec **codec,
  
      enum AVCodecID codec_id);
  
  int open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st);
  
  void close_audio(AVFormatContext *oc, AVStream *st);
  
  void write_audio_frame(uint8_t ** audio_src_data, int audio_src_bufsize);
  
  
  
  int open_audio_input(char* src_filename)
  
  {
  
      int i =0;
  
      /* open input file, and allocate format context */
  
      if (avformat_open_input(&amp;fmt_ctx, src_filename, NULL, NULL) &lt; 0)
  
      {
  
          fprintf(stderr, "Could not open source file %s\n", src_filename);
  
          exit(1);
  
      }
  
  
  
      // Retrieve stream information
  
      if(avformat_find_stream_info(fmt_ctx, NULL)&lt;0)
  
          return -1; // Couldn&#39;t find stream information
  
  
  
      // Dump information about file onto standard error
  
      av_dump_format(fmt_ctx, 0, src_filename, 0);
  
  
  
      // Find the first video stream
  
      for(i=0; inb_streams; i++)
  
      {
  
          if(fmt_ctx->streams[i]->codec->codec_type==AVMEDIA_TYPE_AUDIO)
  
          {
  
              audio_stream_index=i;
  
              break;
  
          }
  
      }
  
      if ( audio_stream_index != -1 )
  
      {
  
          // Get a pointer to the codec context for the audio stream
  
          codec_ctx_audio=fmt_ctx->streams[audio_stream_index]->codec;
  
  
  
          // Find the decoder for the video stream
  
          codec_audio=avcodec_find_decoder(codec_ctx_audio->codec_id);
  
          if(codec_audio==NULL) {
  
              fprintf(stderr, "Unsupported audio codec!\n");
  
              return -1; // Codec not found
  
          }
  
  
  
          // Open codec
  
          AVDictionary *codecDictOptions = NULL;
  
          if(avcodec_open2(codec_ctx_audio, codec_audio, &amp;codecDictOptions)&lt;0)
  
              return -1; // Could not open codec
  
  
  
          // Set up SWR context once you&#39;ve got codec information
  
          swr = swr_alloc();
  
          av_opt_set_int(swr, "in_channel_layout",  codec_ctx_audio->channel_layout, 0);
  
          av_opt_set_int(swr, "out_channel_layout", codec_ctx_audio->channel_layout,  0);
  
          av_opt_set_int(swr, "in_sample_rate",     codec_ctx_audio->sample_rate, 0);
  
          av_opt_set_int(swr, "out_sample_rate",    codec_ctx_audio->sample_rate, 0);
  
          av_opt_set_sample_fmt(swr, "in_sample_fmt",  codec_ctx_audio->sample_fmt, 0);
  
          av_opt_set_sample_fmt(swr, "out_sample_fmt", AV_SAMPLE_FMT_S16,  0);
  
          swr_init(swr);
  
  
  
          // Allocate audio frame
  
          if ( decoded_frame == NULL ) decoded_frame = avcodec_alloc_frame();
  
          int nb_planes = 0;
  
          AVStream* audio_stream = fmt_ctx->streams[audio_stream_index];
  
          nb_planes = av_sample_fmt_is_planar(codec_ctx_audio->sample_fmt) ? codec_ctx_audio->channels : 1;
  
          int tempSize =  sizeof(uint8_t *) * nb_planes;
  
          audio_dst_data = (uint8_t**)av_mallocz(tempSize);
  
          if (!audio_dst_data)
  
          {
  
              fprintf(stderr, "Could not allocate audio data buffers\n");
  
          }
  
          else
  
          {
  
              for ( int i = 0 ; i &lt; nb_planes ; i ++ )
  
              {
  
                  audio_dst_data[i] = NULL;
  
              }
  
          }
  
      }
  
  }
  
  
  
  
  
  int decode_frame()
  
  {
  
      int rv = 0;
  
      got_frame = 0;
  
      if ( fmt_ctx == NULL  )
  
      {
  
          return rv;
  
      }
  
      int ret = 0;
  
      audiobufsize = 0;
  
      rv = av_read_frame(fmt_ctx, &amp;input_packet);
  
      if ( rv &lt; 0 )
  
      {
  
          return rv;
  
      }
  
      rv = decode_packet();
  
      // Free the input_packet that was allocated by av_read_frame
  
      av_free_packet(&amp;input_packet);
  
      return rv;
  
  }
  
  
  
  int decode_packet()
  
  {
  
      int rv = 0;
  
      int ret = 0;
  
  
  
      //audio stream?
  
      if(input_packet.stream_index == audio_stream_index)
  
      {
  
          /* decode audio frame */
  
          rv = avcodec_decode_audio4(codec_ctx_audio, decoded_frame, &amp;got_frame, &amp;input_packet);
  
          if (rv &lt; 0)
  
          {
  
              fprintf(stderr, "Error decoding audio frame\n");
  
              //return ret;
  
          }
  
          else
  
          {
  
              if (got_frame)
  
              {
  
                  if ( audio_dst_data[0] == NULL )
  
                  {
  
                       ret = av_samples_alloc(audio_dst_data, &amp;audio_dst_linesize, decoded_frame->channels,
  
                          decoded_frame->nb_samples, (AVSampleFormat)decoded_frame->format, 1);
  
                      if (ret &lt; 0)
  
                      {
  
                          fprintf(stderr, "Could not allocate audio buffer\n");
  
                          return AVERROR(ENOMEM);
  
                      }
  
                      /* TODO: extend return code of the av_samples_* functions so that this call is not needed */
  
                      audio_dst_bufsize = av_samples_get_buffer_size(NULL, audio_st->codec->channels,
  
                          decoded_frame->nb_samples, (AVSampleFormat)decoded_frame->format, 1);
  
  
  
                      //int16_t* outputBuffer = ...;
  
                      swr_convert(swr, audio_dst_data, out_frame->nb_samples,
  
                                  (const uint8_t **)(decoded_frame->data), decoded_frame->nb_samples);
  
                      //swr_convert( swr, audio_dst_data, out_frame->nb_samples, (const uint8_t**) decoded_frame->extended_data, decoded_frame->nb_samples );
  
                  }
  
                  /* copy audio data to destination buffer:
  
                  * this is required since rawaudio expects non aligned data */
  
                  //av_samples_copy(audio_dst_data, decoded_frame->data, 0, 0,
  
                  //    decoded_frame->nb_samples, decoded_frame->channels, (AVSampleFormat)decoded_frame->format);
  
              }
  
          }
  
      }
  
      return rv;
  
  }
  
  
  
  
  
  int open_encoder(char* output_filename )
  
  {
  
      int rv = 0;
  
  
  
      /* allocate the output media context */
  
      AVOutputFormat *opfmt = NULL;
  
  
  
      avformat_alloc_output_context2(&amp;output_fmt_ctx, opfmt, NULL, output_filename);
  
      if (!output_fmt_ctx) {
  
          printf("Could not deduce output format from file extension: using MPEG.\n");
  
          avformat_alloc_output_context2(&amp;output_fmt_ctx, NULL, "mpeg", output_filename);
  
      }
  
      if (!output_fmt_ctx) {
  
          rv = -1;
  
      }
  
      else
  
      {
  
          output_format = output_fmt_ctx->oformat;
  
      }
  
  
  
      /* Add the audio stream using the default format codecs
  
      * and initialize the codecs. */
  
      audio_st = NULL;
  
  
  
      if ( output_fmt_ctx )
  
      {
  
          if (output_format->audio_codec != AV_CODEC_ID_NONE)
  
          {
  
              audio_st = add_audio_stream(output_fmt_ctx, &amp;audio_codec, output_format->audio_codec);
  
          }
  
  
  
          /* Now that all the parameters are set, we can open the audio and
  
          * video codecs and allocate the necessary encode buffers. */
  
          if (audio_st)
  
          {
  
              rv = open_audio(output_fmt_ctx, audio_codec, audio_st);
  
              if ( rv &lt; 0 ) return rv;
  
          }
  
  
  
          av_dump_format(output_fmt_ctx, 0, output_filename, 1);
  
          /* open the output file, if needed */
  
          if (!(output_format->flags &amp; AVFMT_NOFILE))
  
          {
  
              if (avio_open(&amp;output_fmt_ctx->pb, output_filename, AVIO_FLAG_WRITE) &lt; 0) {
  
                  fprintf(stderr, "Could not open &#39;%s&#39;\n", output_filename);
  
                  rv = -1;
  
              }
  
              else
  
              {
  
                  /* Write the stream header, if any. */
  
                  if (avformat_write_header(output_fmt_ctx, NULL) &lt; 0)
  
                  {
  
                      fprintf(stderr, "Error occurred when opening output file\n");
  
                      rv = -1;
  
                  }
  
              }
  
          }
  
      }
  
  
  
      return rv;
  
  }
  
  
  
  AVStream *add_audio_stream(AVFormatContext *oc, AVCodec **codec,
  
      enum AVCodecID codec_id)
  
  {
  
      AVCodecContext *c;
  
      AVStream *st;
  
  
  
      /* find the audio encoder */
  
      *codec = avcodec_find_encoder(codec_id);
  
      if (!(*codec)) {
  
          fprintf(stderr, "Could not find codec\n");
  
          exit(1);
  
      }
  
  
  
      st = avformat_new_stream(oc, *codec);
  
      if (!st) {
  
          fprintf(stderr, "Could not allocate stream\n");
  
          exit(1);
  
      }
  
      st->id = 1;
  
  
  
      c = st->codec;
  
  
  
      /* put sample parameters */
  
      c->sample_fmt  = AV_SAMPLE_FMT_S16;
  
      c->bit_rate    = audio_bit_rate;
  
      c->sample_rate = audio_sample_rate;
  
      c->channels    = audio_channels;
  
  
  
      // some formats want stream headers to be separate
  
      if (oc->oformat->flags &amp; AVFMT_GLOBALHEADER)
  
          c->flags |= CODEC_FLAG_GLOBAL_HEADER;
  
  
  
      return st;
  
  }
  
  
  
  int open_audio(AVFormatContext *oc, AVCodec *codec, AVStream *st)
  
  {
  
      int ret=0;
  
      AVCodecContext *c;
  
  
  
      st->duration = fmt_ctx->duration;
  
      c = st->codec;
  
  
  
      /* open it */
  
      ret = avcodec_open2(c, codec, NULL) ;
  
      if ( ret &lt; 0)
  
      {
  
          fprintf(stderr, "could not open codec\n");
  
          return -1;
  
          //exit(1);
  
      }
  
  
  
      if (c->codec->capabilities &amp; CODEC_CAP_VARIABLE_FRAME_SIZE)
  
          audio_input_frame_size = 10000;
  
      else
  
          audio_input_frame_size = c->frame_size;
  
      int tempSize = audio_input_frame_size *
  
          av_get_bytes_per_sample(c->sample_fmt) *
  
          c->channels;
  
      return ret;
  
  }
  
  
  
  void close_audio(AVFormatContext *oc, AVStream *st)
  
  {
  
      avcodec_close(st->codec);
  
  }
  
  
  
  void write_audio_frame(uint8_t ** audio_src_data, int audio_src_bufsize)
  
  {
  
      AVFormatContext *oc = output_fmt_ctx;
  
      AVStream *st = audio_st;
  
      if ( oc == NULL || st == NULL ) return;
  
      AVCodecContext *c;
  
      AVPacket pkt = { 0 }; // data and size must be 0;
  
      int got_packet;
  
  
  
      av_init_packet(&amp;pkt);
  
      c = st->codec;
  
  
  
      out_frame->nb_samples = audio_input_frame_size;
  
      int buf_size =         audio_src_bufsize *
  
          av_get_bytes_per_sample(c->sample_fmt) *
  
          c->channels;
  
      avcodec_fill_audio_frame(out_frame, c->channels, c->sample_fmt,
  
          (uint8_t *) *audio_src_data,
  
          buf_size, 1);
  
      avcodec_encode_audio2(c, &amp;pkt, out_frame, &amp;got_packet);
  
      if (!got_packet)
  
      {
  
      }
  
      else
  
      {
  
          if (pkt.pts != AV_NOPTS_VALUE)
  
              pkt.pts =  av_rescale_q(pkt.pts, st->codec->time_base, st->time_base);
  
          if (pkt.dts != AV_NOPTS_VALUE)
  
              pkt.dts = av_rescale_q(pkt.dts, st->codec->time_base, st->time_base);
  
          if ( c &amp;&amp; c->coded_frame &amp;&amp; c->coded_frame->key_frame)
  
              pkt.flags |= AV_PKT_FLAG_KEY;
  
  
  
           pkt.stream_index = st->index;
  
          pkt.flags |= AV_PKT_FLAG_KEY;
  
          /* Write the compressed frame to the media file. */
  
          if (av_interleaved_write_frame(oc, &amp;pkt) != 0)
  
          {
  
              fprintf(stderr, "Error while writing audio frame\n");
  
              exit(1);
  
          }
  
      }
  
      av_free_packet(&amp;pkt);
  
  }
  
  
  
  
  
  void write_delayed_frames(AVFormatContext *oc, AVStream *st)
  
  {
  
      AVCodecContext *c = st->codec;
  
      int got_output = 0;
  
      int ret = 0;
  
      AVPacket pkt;
  
      pkt.data = NULL;
  
      pkt.size = 0;
  
      av_init_packet(&amp;pkt);
  
      int i = 0;
  
      for (got_output = 1; got_output; i++)
  
      {
  
          ret = avcodec_encode_audio2(c, &amp;pkt, NULL, &amp;got_output);
  
          if (ret &lt; 0)
  
          {
  
              fprintf(stderr, "error encoding frame\n");
  
              exit(1);
  
          }
  
          static int64_t tempPts = 0;
  
          static int64_t tempDts = 0;
  
          /* If size is zero, it means the image was buffered. */
  
          if (got_output)
  
          {
  
              if (pkt.pts != AV_NOPTS_VALUE)
  
                  pkt.pts =  av_rescale_q(pkt.pts, st->codec->time_base, st->time_base);
  
              if (pkt.dts != AV_NOPTS_VALUE)
  
                  pkt.dts = av_rescale_q(pkt.dts, st->codec->time_base, st->time_base);
  
              if ( c &amp;&amp; c->coded_frame &amp;&amp; c->coded_frame->key_frame)
  
                  pkt.flags |= AV_PKT_FLAG_KEY;
  
  
  
              pkt.stream_index = st->index;
  
              /* Write the compressed frame to the media file. */
  
              ret = av_interleaved_write_frame(oc, &amp;pkt);
  
          }
  
          else
  
          {
  
              ret = 0;
  
          }
  
          av_free_packet(&amp;pkt);
  
      }
  
  }
  
  
  
  int main(int argc, char **argv)
  
  {
  
      /* register all formats and codecs */
  
      av_register_all();
  
      avcodec_register_all();
  
      avformat_network_init();
  
      avdevice_register_all();
  
      int i =0;
  
      int ret=0;
  
      char src_filename[90] = "test_a.webm";
  
      char dst_filename[90] = "output.aac";
  
      open_audio_input(src_filename);
  
      if ( codec_ctx_audio->bit_rate == 0 ) codec_ctx_audio->bit_rate = 112000;
  
      audio_bit_rate        = codec_ctx_audio->bit_rate;
  
      audio_sample_rate    = codec_ctx_audio->sample_rate;
  
      audio_channels        = codec_ctx_audio->channels;
  
      open_encoder( dst_filename );
  
      while(1)
  
      {
  
          int rv = decode_frame();
  
          if ( rv &lt; 0 )
  
          {
  
              break;
  
          }
  
  
  
          if (audio_st)
  
          {
  
              audio_pts = (double)audio_st->pts.val * audio_st->time_base.num /
  
                  audio_st->time_base.den;
  
          }
  
          else
  
          {
  
              audio_pts = 0.0;
  
          }
  
          if ( codec_ctx_audio )
  
          {
  
              if ( got_frame)
  
              {
  
                  write_audio_frame( audio_dst_data, audio_dst_bufsize );
  
              }
  
          }
  
          if ( audio_dst_data[0] )
  
          {
  
              av_freep(&amp;audio_dst_data[0]);
  
              audio_dst_data[0] = NULL;
  
          }
  
          printf("\naudio_pts: %.3f", audio_pts);
  
      }
  
      while(1)
  
      {
  
          if ( audio_dst_data &amp;&amp; audio_dst_data[0] )
  
          {
  
              av_freep(&amp;audio_dst_data[0]);
  
              audio_dst_data[0] = NULL;
  
          }
  
          ret = av_samples_alloc(audio_dst_data, NULL, codec_ctx_audio->channels,
  
              decoded_frame->nb_samples, AV_SAMPLE_FMT_S16, 0);
  
          ret = swr_convert(swr, audio_dst_data, out_frame->nb_samples,NULL, 0);
  
          if ( ret &lt;= 0 ) break;
  
          write_audio_frame( audio_dst_data, audio_dst_bufsize );
  
      }
  
      write_delayed_frames( output_fmt_ctx, audio_st );
  
      av_write_trailer(output_fmt_ctx);
  
      close_audio( output_fmt_ctx, audio_st);
  
      swr_free(&amp;swr);
  
      avcodec_free_frame(&amp;out_frame);
  
      getch();
  
      return 0;
  
  }
  
  </queue></deque></map></vector></string></fstream></iostream>

  "test_a.webm" input file results in longer duration (40 second output), and if I change it to "jet.webm", it is converted fine.

  Both input files are approximately 18 second duration.

  For reference, these files can be downloaded from links below :

  http://www.filedropper.com/testa ,
  http://www.filedropper.com/jet

  Alternatively, they are zipped and uploaded elsewhere as well :

  http://www.files.com/shared/52c3eefe990ea/test_audio_files.zip

  Could someone kindly guide on what I am doing wrong here ?

  Thanks in advance...

  p.s. These files are taken/extracted from different online sources/demos.

  Edit 2-1-14 : After debugging, I can see audio_pts variable is being populated incorrectly. It relies on audio_st->pts.val, which is automatically calculated upon calling av_interleaved_write_frame() function. I cannot step inside av_interleaved_write_frame() function since I am on Windows, using libav dlls/libs.

  So,

  For jet.webm file (whose conversion is fine), audio_st->pts.val goes till maximum : 1665567, and audio_pts becomes :

  1665567*1/90000 = 18.5063

  For test_a.webm file (whose conversion is bad), audio_st->pts.val goes till maximum : 3606988, and audio_pts becomes :

  3606988*1/90000 = 40.0776

  • reference line : audio_pts = (double)audio_st->pts.val * audio_st->time_base.num /
    audio_st->time_base.den ;

  Since PTS is very off, it shouldn't be playing fine logically as well. But I cannot say av_interleaved_write_frame() function is doing it wrong ; surely something cleaner can be managed on my end.

  Edit 3-1-14 : Discovered one more thing : while reading jet.webm file, decoded frame's nb_sample are always 1024 (except for 1st frame : 576), but in case of test_a.webm file, nb_samples are either 1024, or 128, with exceptions of 576 (less frequent). If I ignore writing of frame when nb_sample is 128, I get approximately same file length in the end, but you can hear bits and pieces are missing here and there.

  How can I deal with this ?