Recherche avancée

Sur d’autres sites (13199)

• audio convert to mp3,pcm and vox using ffmpeg

  8 juillet 2014, par user3789242

  Please can someone help me with the code for ffmpeg.
  I have to use ffmpeg to convert a recorder voice (using HTML5) into mp3,pcm or vox depending on the user’s selection.
  I don’t know how to write the code for ffmpeg if some one can help me with the code or libraries.
  Thank you in advance.

  Here is my code for recording the voice with a visualizer :

  // 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));
  
  }
  
  }

• ffmpeg concatenation with -filter_complex

  16 octobre 2018, par Igniter

  I’ve seen several similar questions but none of them actually helped in my case.
  Getting this error while trying to join 1 audio and 4 video files of different nature and resolutions.

  ffmpeg -i 0.mp3 -i 1.mp4 -i 2.mkv -i 3.mkv -i 4.webm \
  
      -filter_complex [0:a:0][1:v:0][2:v:0][3:v:0][4:v:0]concat=n=5:v=1:a=1[outv][outa] \
  
      -map "[outv]" -map "[outa]" output.mp4

  All this gives the following error :

  Stream specifier ':a:0' in filtergraph description [0:a:0][1:v:0][2:v:0][3:v:0][4:v:0]concat=n=5:v=1:a=1[outv][outa] matches no streams.

  Straight concatenation -i "concat:0.mp3|1.mp4..." also doesn’t work as expected due to different resolutions and video formats. All methods syntax was taken from official documentation but there should be something that I’ve missed here.

  Full output log :

  ffmpeg version 3.4.4-0ubuntu0.18.04.1 Copyright (c) 2000-2018 the FFmpeg developers
  
    built with gcc 7 (Ubuntu 7.3.0-16ubuntu3)
  
    configuration: --prefix=/usr --extra-version=0ubuntu0.18.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --enable-gpl --disable-stripping --enable-avresample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librubberband --enable-librsvg --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-omx --enable-openal --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libopencv --enable-libx264 --enable-shared
  
    libavutil      55. 78.100 / 55. 78.100
  
    libavcodec     57.107.100 / 57.107.100
  
    libavformat    57. 83.100 / 57. 83.100
  
    libavdevice    57. 10.100 / 57. 10.100
  
    libavfilter     6.107.100 /  6.107.100
  
    libavresample   3.  7.  0 /  3.  7.  0
  
    libswscale      4.  8.100 /  4.  8.100
  
    libswresample   2.  9.100 /  2.  9.100
  
    libpostproc    54.  7.100 / 54.  7.100
  
  Input #0, mp3, from 'mp3/10.mp3':
  
    Metadata:
  
      album_artist    : artist
  
      title           : title
  
      artist          : 10
  
      album           : 12
  
      track           : 1
  
      VideoKind       : 2
  
      date            : 2009
  
    Duration: 00:06:00.44, start: 0.025056, bitrate: 64 kb/s
  
      Stream #0:0: Audio: mp3, 44100 Hz, stereo, s16p, 64 kb/s
  
      Metadata:
  
        encoder         : LAME3.98r
  
      Stream #0:1: Video: mjpeg, yuvj420p(pc, bt470bg/unknown/unknown), 200x200 [SAR 72:72 DAR 1:1], 90k tbr, 90k tbn, 90k tbc
  
      Metadata:
  
        comment         : Cover (front)
  
  Input #1, matroska,webm, from '1.mp4':
  
    Metadata:
  
      MINOR_VERSION   : 0
  
      COMPATIBLE_BRANDS: iso6avc1mp41
  
      MAJOR_BRAND     : dash
  
      ENCODER         : Lavf57.83.100
  
    Duration: 00:01:53.05, start: 0.007000, bitrate: 2292 kb/s
  
      Stream #1:0: Video: h264 (High), yuv420p(tv, bt709, progressive), 1920x1080 [SAR 1:1 DAR 16:9], 24 fps, 24 tbr, 1k tbn, 48 tbc (default)
  
      Metadata:
  
        HANDLER_NAME    : VideoHandler
  
        DURATION        : 00:01:53.048000000
  
  Input #2, matroska,webm, from '2.mkv':
  
    Metadata:
  
      MINOR_VERSION   : 0
  
      COMPATIBLE_BRANDS: iso6avc1mp41
  
      MAJOR_BRAND     : dash
  
      ENCODER         : Lavf57.83.100
  
    Duration: 00:02:08.09, start: 0.007000, bitrate: 1607 kb/s
  
      Stream #2:0: Video: h264 (High), yuv420p(tv, bt709, progressive), 1920x1080 [SAR 1:1 DAR 16:9], 24 fps, 24 tbr, 1k tbn, 48 tbc (default)
  
      Metadata:
  
        HANDLER_NAME    : VideoHandler
  
        DURATION        : 00:02:08.090000000
  
  Input #3, matroska,webm, from '3.mkv':
  
    Metadata:
  
      MINOR_VERSION   : 0
  
      COMPATIBLE_BRANDS: iso6avc1mp41
  
      MAJOR_BRAND     : dash
  
      ENCODER         : Lavf57.83.100
  
    Duration: 00:01:37.05, start: 0.007000, bitrate: 3525 kb/s
  
      Stream #3:0: Video: h264 (High), yuv420p(tv, bt709, progressive), 1920x1080 [SAR 1:1 DAR 16:9], 24 fps, 24 tbr, 1k tbn, 48 tbc (default)
  
      Metadata:
  
        HANDLER_NAME    : VideoHandler
  
        DURATION        : 00:01:37.048000000
  
  Input #4, matroska,webm, from '4.webm':
  
    Metadata:
  
      MINOR_VERSION   : 0
  
      COMPATIBLE_BRANDS: iso6avc1mp41
  
      MAJOR_BRAND     : dash
  
      ENCODER         : Lavf57.83.100
  
    Duration: 00:01:45.13, start: 0.007000, bitrate: 3685 kb/s
  
      Stream #4:0: Video: h264 (High), yuv420p(tv, bt709, progressive), 1920x1080 [SAR 1:1 DAR 16:9], 24 fps, 24 tbr, 1k tbn, 48 tbc (default)
  
      Metadata:
  
        HANDLER_NAME    : VideoHandler
  
        DURATION        : 00:01:45.131000000
  
  Stream specifier ':a:0' in filtergraph description [0:a:0][1:v:0][2:v:0][3:v:0][4:v:0]concat=n=5:v=1:a=1[outv][outa] matches no streams.

• Problems with Python's azure.cognitiveservices.speech when installing together with FFmpeg in a Linux web app

  15 mai 2024, par Kakobo kakobo

  I need some help.
I'm building an web app that takes any audio format, converts into a .wav file and then passes it to 'azure.cognitiveservices.speech' for transcription.I'm building the web app via a container Dockerfile as I need to install ffmpeg to be able to convert non ".wav" audio files to ".wav" (as azure speech services only process wav files). For some odd reason, the 'speechsdk' class of 'azure.cognitiveservices.speech' fails to work when I install ffmpeg in the web app. The class works perfectly fine when I install it without ffpmeg or when i build and run the container in my machine.

  


  I have placed debug print statements in the code. I can see the class initiating, for some reason it does not buffer in the same when when running it locally in my machine. The routine simply stops without any reason.

  


  Has anybody experienced a similar issue with azure.cognitiveservices.speech conflicting with ffmpeg ?

  


  Here's my Dockerfile :

  


  # Use an official Python runtime as a parent imageFROM python:3.11-slim

#Version RunRUN echo "Version Run 1..."

Install ffmpeg

RUN apt-get update && apt-get install -y ffmpeg && # Ensure ffmpeg is executablechmod a+rx /usr/bin/ffmpeg && # Clean up the apt cache by removing /var/lib/apt/lists saves spaceapt-get clean && rm -rf /var/lib/apt/lists/*

//Set the working directory in the container

WORKDIR /app

//Copy the current directory contents into the container at /app

COPY . /app

//Install any needed packages specified in requirements.txt

RUN pip install --no-cache-dir -r requirements.txt

//Make port 80 available to the world outside this container

EXPOSE 8000

//Define environment variable

ENV NAME World

//Run main.py when the container launches

CMD ["streamlit", "run", "main.py", "--server.port", "8000", "--server.address", "0.0.0.0"]`and here's my python code:


  


  def transcribe_audio_continuous_old(temp_dir, audio_file, language):
    speech_key = azure_speech_key
    service_region = azure_speech_region

    time.sleep(5)
    print(f"DEBUG TIME BEFORE speechconfig")

    ran = generate_random_string(length=5)
    temp_file = f"transcript_key_{ran}.txt"
    output_text_file = os.path.join(temp_dir, temp_file)
    speech_recognition_language = set_language_to_speech_code(language)
    
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    speech_config.speech_recognition_language = speech_recognition_language
    audio_input = speechsdk.AudioConfig(filename=os.path.join(temp_dir, audio_file))
        
    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_input, language=speech_recognition_language)
    done = False
    transcript_contents = ""

    time.sleep(5)
    print(f"DEBUG TIME AFTER speechconfig")
    print(f"DEBUG FIle about to be passed {audio_file}")

    try:
        with open(output_text_file, "w", encoding=encoding) as file:
            def recognized_callback(evt):
                print("Start continuous recognition callback.")
                print(f"Recognized: {evt.result.text}")
                file.write(evt.result.text + "\n")
                nonlocal transcript_contents
                transcript_contents += evt.result.text + "\n"

            def stop_cb(evt):
                print("Stopping continuous recognition callback.")
                print(f"Event type: {evt}")
                speech_recognizer.stop_continuous_recognition()
                nonlocal done
                done = True
            
            def canceled_cb(evt):
                print(f"Recognition canceled: {evt.reason}")
                if evt.reason == speechsdk.CancellationReason.Error:
                    print(f"Cancellation error: {evt.error_details}")
                nonlocal done
                done = True

            speech_recognizer.recognized.connect(recognized_callback)
            speech_recognizer.session_stopped.connect(stop_cb)
            speech_recognizer.canceled.connect(canceled_cb)

            speech_recognizer.start_continuous_recognition()
            while not done:
                time.sleep(1)
                print("DEBUG LOOPING TRANSCRIPT")

    except Exception as e:
        print(f"An error occurred: {e}")

    print("DEBUG DONE TRANSCRIPT")

    return temp_file, transcript_contents


  


  The transcript this callback works fine locally, or when installed without ffmpeg in the linux web app. Not sure why it conflicts with ffmpeg when installed via container dockerfile. The code section that fails can me found on note #NOTE DEBUG"