Recherche avancée

Sur d’autres sites (12386)

• Recording voice using HTML5 and processing it with ffmpeg

  22 mars 2015, par user3789242

  I need to use ffmpeg in my javascript/HTML5 project which allows the user to select the format he wants the audio to open with.I don’t know anything about ffmpeg and I’ve been doing lots of research I don’t know how to use it in my project. I found an example https://github.com/sopel39/audioconverter.js but the problem how can I install the ffmpeg.js which is 8 mg to m project. please if someone can help me I’ll be very thankfull
  here is my full code :

  the javascript page :

  // variables
  
  var leftchannel = [];
  
  var rightchannel = [];
  
  var recorder = null;
  
  var recording = false;
  
  var recordingLength = 0;
  
  var volume = null;
  
  var audioInput = null;
  
  var sampleRate = 44100;
  
  var audioContext = null;
  
  var context = null;
  
  var outputString;
  
  
  
  
  
  
  
  if (!navigator.getUserMedia)
  
  navigator.getUserMedia = navigator.getUserMedia ||
  
                           navigator.webkitGetUserMedia ||
  
                           navigator.mozGetUserMedia || 
  
                           navigator.msGetUserMedia;
  
  
  
  if (navigator.getUserMedia){
  
  navigator.getUserMedia({audio:true}, success, function(e) {
  
  alert('Error capturing audio.');
  
  });
  
  } else alert('getUserMedia not supported in this browser.');
  
  
  
  
  
  
  
  function getVal(value)
  
    {
  
  
  
  // if R is pressed, we start recording
  
  if ( value == "record"){
  
      recording = true;
  
      // reset the buffers for the new recording
  
      leftchannel.length = rightchannel.length = 0;
  
      recordingLength = 0;
  
      document.getElementById('output').innerHTML="Recording now...";
  
  
  
   // if S is pressed, we stop the recording and package the WAV file
  
   } else if ( value == "stop" ){
  
  
  
      // we stop recording
  
      recording = false;
  
      document.getElementById('output').innerHTML="Building wav file...";
  
  
  
      // we flat the left and right channels down
  
      var leftBuffer = mergeBuffers ( leftchannel, recordingLength );
  
      var rightBuffer = mergeBuffers ( rightchannel, recordingLength );
  
      // we interleave both channels together
  
      var interleaved = interleave ( leftBuffer, rightBuffer );
  
  
  
  
  
  
  
      var buffer = new ArrayBuffer(44 + interleaved.length * 2);
  
      var view = new DataView(buffer);
  
  
  
      // RIFF chunk descriptor
  
      writeUTFBytes(view, 0, 'RIFF');
  
      view.setUint32(4, 44 + interleaved.length * 2, true);
  
      writeUTFBytes(view, 8, 'WAVE');
  
      // FMT sub-chunk
  
      writeUTFBytes(view, 12, 'fmt ');
  
      view.setUint32(16, 16, true);
  
      view.setUint16(20, 1, true);
  
      // stereo (2 channels)
  
      view.setUint16(22, 2, true);
  
      view.setUint32(24, sampleRate, true);
  
      view.setUint32(28, sampleRate * 4, true);
  
      view.setUint16(32, 4, true);
  
      view.setUint16(34, 16, true);
  
      // data sub-chunk
  
      writeUTFBytes(view, 36, 'data');
  
      view.setUint32(40, interleaved.length * 2, true);
  
  
  
  
  
      var lng = interleaved.length;
  
      var index = 44;
  
      var volume = 1;
  
      for (var i = 0; i < lng; i++){
  
          view.setInt16(index, interleaved[i] * (0x7FFF * volume), true);
  
          index += 2;
  
      }
  
  
  
      var blob = new Blob ( [ view ], { type : 'audio/wav' } );
  
  
  
      // let's save it locally
  
  
  
      document.getElementById('output').innerHTML='Handing off the file now...';
  
      var url = (window.URL || window.webkitURL).createObjectURL(blob);
  
  
  
      var li = document.createElement('li');
  
      var au = document.createElement('audio');
  
      var hf = document.createElement('a');
  
  
  
      au.controls = true;
  
      au.src = url;
  
      hf.href = url;
  
      hf.download = 'audio_recording_' + new Date().getTime() + '.wav';
  
      hf.innerHTML = hf.download;
  
      li.appendChild(au);
  
      li.appendChild(hf);
  
      recordingList.appendChild(li);
  
  
  
  }
  
  }
  
  
  
  
  
  function success(e){
  
  
  
  audioContext = window.AudioContext || window.webkitAudioContext;
  
  context = new audioContext();
  
  
  
  
  
  volume = context.createGain();
  
  
  
  // creates an audio node from the microphone incoming stream(source)
  
  source = context.createMediaStreamSource(e);
  
  
  
  // connect the stream(source) to the gain node
  
  source.connect(volume);
  
  
  
  var bufferSize = 2048;
  
  
  
  recorder = context.createScriptProcessor(bufferSize, 2, 2);
  
  
  
  //node for the visualizer
  
  analyser = context.createAnalyser();
  
  analyser.smoothingTimeConstant = 0.3;
  
  analyser.fftSize = 512;
  
  
  
  splitter = context.createChannelSplitter();
  
  //when recording happens
  
  recorder.onaudioprocess = function(e){
  
  
  
      if (!recording) return;
  
      var left = e.inputBuffer.getChannelData (0);
  
      var right = e.inputBuffer.getChannelData (1);
  
  
  
      leftchannel.push (new Float32Array (left));
  
      rightchannel.push (new Float32Array (right));
  
      recordingLength += bufferSize;
  
  
  
      // get the average for the first channel
  
      var array =  new Uint8Array(analyser.frequencyBinCount);
  
      analyser.getByteFrequencyData(array);
  
  
  
      var c=document.getElementById("myCanvas");
  
      var ctx = c.getContext("2d");
  
      // clear the current state
  
      ctx.clearRect(0, 0, 1000, 325);
  
      var gradient = ctx.createLinearGradient(0,0,0,300);
  
      gradient.addColorStop(1,'#000000');
  
      gradient.addColorStop(0.75,'#ff0000');
  
      gradient.addColorStop(0.25,'#ffff00');
  
      gradient.addColorStop(0,'#ffffff');
  
      // set the fill style
  
      ctx.fillStyle=gradient;
  
      drawSpectrum(array);
  
      function drawSpectrum(array) {
  
          for ( var i = 0; i < (array.length); i++ ){
  
                  var value = array[i];
  
                  ctx.fillRect(i*5,325-value,3,325);
  
              } 
  
  
  
      }
  
  }
  
  
  
  function getAverageVolume(array) {
  
      var values = 0;
  
      var average;
  
  
  
      var length = array.length;
  
  
  
      // get all the frequency amplitudes
  
      for (var i = 0; i < length; i++) {
  
          values += array[i];
  
      }
  
  
  
      average = values / length;
  
      return average;
  
  }
  
  
  
      // we connect the recorder(node to destination(speakers))
  
      volume.connect(splitter);
  
      splitter.connect(analyser, 0, 0);
  
  
  
      analyser.connect(recorder);
  
      recorder.connect(context.destination);
  
  
  
  }
  
  
  
  
  
  
  
  
  
  function mergeBuffers(channelBuffer, recordingLength){
  
  var result = new Float32Array(recordingLength);
  
  var offset = 0;
  
  var lng = channelBuffer.length;
  
  for (var i = 0; i < lng; i++){
  
  var buffer = channelBuffer[i];
  
  result.set(buffer, offset);
  
  offset += buffer.length;
  
  }
  
      return result;
  
     }
  
  
  
  function interleave(leftChannel, rightChannel){
  
  var length = leftChannel.length + rightChannel.length;
  
  var result = new Float32Array(length);
  
  
  
  var inputIndex = 0;
  
  
  
  for (var index = 0; index < length; ){
  
   result[index++] = leftChannel[inputIndex];
  
   result[index++] = rightChannel[inputIndex];
  
   inputIndex++;
  
  }
  
  return result;
  
  }
  
  
  
  
  
  function writeUTFBytes(view, offset, string){ 
  
  var lng = string.length;
  
  for (var i = 0; i < lng; i++){
  
  
  
  view.setUint8(offset + i, string.charCodeAt(i));
  
  }
  
  }

  and here is the html code :

      
  
      
  
      
  
      <code class="echappe-js">&lt;script src=&quot;http://stackoverflow.com/feeds/tag/js/functions.js&quot;&gt;&lt;/script&gt;
      
  
      
  
  
  
  

• FFmpeg remove silence with exact duration detected by detect silence

  17 mars 2021, par dav

  I have an audio file, that have some silences, which I am detecting with ffmpeg detectsilence and then trying to remove with removesilence, however there is some strange behavior. Specifically :

  


  1) File's Basic info based on ffprobe show_streams

  


  Input #0, mp3, from 'my_file.mp3':
  Metadata:
    encoder         : Lavf58.64.100
  Duration: 00:00:25.22, start: 0.046042, bitrate: 32 kb/s
    Stream #0:0: Audio: mp3, 24000 Hz, mono, fltp, 32 kb/s


  


  2) Using detectsilence

  


  ffmpeg -i my_file.mp3 -af silencedetect=noise=-50dB:d=0.2 -f null -


  


  I get this result

  


  [mp3float @ 000001ee50074280] overread, skip -7 enddists: -1 -1
[silencedetect @ 000001ee5008a1c0] silence_start: 6.21417
[silencedetect @ 000001ee5008a1c0] silence_end: 6.91712 | silence_duration: 0.702958
[silencedetect @ 000001ee5008a1c0] silence_start: 16.44
[silencedetect @ 000001ee5008a1c0] silence_end: 17.1547 | silence_duration: 0.714708
[mp3float @ 000001ee50074280] overread, skip -10 enddists: -3 -3
[mp3float @ 000001ee50074280] overread, skip -5 enddists: -4 -4
[silencedetect @ 000001ee5008a1c0] silence_start: 24.4501
size=N/A time=00:00:25.17 bitrate=N/A speed=1.32e+03x
video:0kB audio:1180kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
[silencedetect @ 000001ee5008a1c0] silence_end: 25.176 | silence_duration: 0.725917


  


  That also match the values and points based on Adobe Audition

  


  

  


  So far all good.

  


  3) Now, based on some calculations (which is based on application's logic on what should be the final duration of the audio) I am trying to delete the silence with "0.725917"s duration. For that, based on ffmpeg docs (https://ffmpeg.org/ffmpeg-filters.html#silencedetect)

  


  


  Trim all silence encountered from beginning to end where there is more
than 1 second of silence in audio :
silenceremove=stop_periods=-1:stop_duration=1:stop_threshold=-90dB

  


  


  I run this command

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.72 result1.mp3


  


  So, I am expecting that it should delete only the silence with "0.725917" duration (the last one in the above image), however it is deleting the silence that starts at 16.44s with duration of "0.714708"s. Please see the following comparison :

  


  

  


  4) Running detectsilence on result1.mp3 with same options gives even stranger results

  


  ffmpeg -i result1.mp3 -af silencedetect=noise=-50dB:d=0.2 -f null -


  


  result

  


  [mp3float @ 0000017723404280] overread, skip -5 enddists: -4 -4
[silencedetect @ 0000017723419540] silence_start: 6.21417
[silencedetect @ 0000017723419540] silence_end: 6.92462 | silence_duration: 0.710458
[mp3float @ 0000017723404280] overread, skip -7 enddists: -6 -6
[mp3float @ 0000017723404280] overread, skip -7 enddists: -2 -2
[mp3float @ 0000017723404280] overread, skip -6 enddists: -1 -1
    Last message repeated 1 times
[silencedetect @ 0000017723419540] silence_start: 23.7308
size=N/A time=00:00:24.45 bitrate=N/A speed=1.33e+03x
video:0kB audio:1146kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
[silencedetect @ 0000017723419540] silence_end: 24.456 | silence_duration: 0.725167


  


  So, the results are :

  


  

  • With command to remove silences that are longer than "0.72 second", a silence that was "0.714708"s, got removed and - a silence with "0.725917"s remained as is (well, actually changed a little - as per 3rd point)

  


  • The first silence that had started at "6.21417" and had a duration of "0.702958"s, suddenly now has a duration of "0.710458"s

  


  • The 3rd silence that had started at "24.4501" (which now starts at 23.7308 - obviously because the 2nd silence was removed) and had a duration of "0.725917", now suddenly is "0.725167"s (this one is not a big difference, but still why even removing other silence, this silence's duration should change at all).

  


  


  Accordingly the expected results are :

  


  

  • Only the silences that match the provided condition (stop_duration=0.72) should be removed. In this specific example only the last one, but in general any silence that matches the condition of the length - irrelevant of their positioning (start, end or in the middle)

  


  • Other silences should remain with same exact duration they were before

  


  


  FFMpeg : 4.2.4-1ubuntu0.1, Ubuntu : 20.04.2

  


  Some attempts and results, while playing with ffmpeg options

  


  a)

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.72:detection=peak tmp1.mp3


  


  result :
First and second silences are removed, 3rd silence's duration remains exactly the same

  


  b)

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.71 tmp_0.71.mp3


  


  result :
First and second silences are removed, 3rd silence remains, but the duration becomes "0.72075"s

  


  c)

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.7 tmp_0.7.mp3


  


  result :
all 3 silence are removed

  


  d) the edge case

  


  this command still removes the second silence (after which the first silence become exactly as in point #4 and last silence becomes "0.721375")

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.72335499999 tmp_0.72335499999.mp3


  


  but this one, again does not remove any silence :

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.723355 tmp_0.723355.mp3


  


  e) window param case 0.03

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.72:window=0.03 window_0.03.mp3


  


  does not remove any silence, but the detect silence

  


  ffmpeg -i window_0.03.mp3 -af silencedetect=noise=-50dB:d=0.2 -f null -


  


  gives this result (compare with silences in result1.mp3 - from point #4 )

  


  [mp3float @ 000001c5c8824280] overread, skip -5 enddists: -4 -4
[silencedetect @ 000001c5c883a040] silence_start: 6.21417
[silencedetect @ 000001c5c883a040] silence_end: 6.92462 | silence_duration: 0.710458
[mp3float @ 000001c5c8824280] overread, skip -7 enddists: -6 -6
[mp3float @ 000001c5c8824280] overread, skip -7 enddists: -2 -2
[silencedetect @ 000001c5c883a040] silence_start: 16.4424
[silencedetect @ 000001c5c883a040] silence_end: 17.1555 | silence_duration: 0.713167
[mp3float @ 000001c5c8824280] overread, skip -6 enddists: -1 -1
    Last message repeated 1 times
[silencedetect @ 000001c5c883a040] silence_start: 24.4508
size=N/A time=00:00:25.17 bitrate=N/A speed=1.24e+03x
video:0kB audio:1180kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
[silencedetect @ 000001c5c883a040] silence_end: 25.176 | silence_duration: 0.725167


  


  f) window case 0.01

  


  ffmpeg -i my_file.mp3 -af silenceremove=stop_periods=-1:stop_threshold=-50dB:stop_duration=0.72:window=0.01 window_0.01.mp3


  


  removes first and second silences, the detect silence with same params has the following result

  


  [mp3float @ 000001ea631d4280] overread, skip -5 enddists: -4 -4
    Last message repeated 1 times
[mp3float @ 000001ea631d4280] overread, skip -7 enddists: -2 -2
[mp3float @ 000001ea631d4280] overread, skip -6 enddists: -1 -1
    Last message repeated 1 times
[silencedetect @ 000001ea631ea1c0] silence_start: 23.0108
size=N/A time=00:00:23.73 bitrate=N/A speed=1.2e+03x
video:0kB audio:1113kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
[silencedetect @ 000001ea631ea1c0] silence_end: 23.736 | silence_duration: 0.725167


  


  ---

  


  Any thoughts, ideas, points are much appreciated.

  


• Revision 34657 : lister les plugins non utilises (le glob() est pourri, qui fait mieux)

  23 janvier 2010, par fil@… — Log

  lister les plugins non utilises (le glob() est pourri, qui fait mieux)