Recherche avancée

Sur d’autres sites (3240)

• How to fetch video frame and its timestamp from ffmpeg to python code

  14 février 2017, par vijiboy

  Searching for an alternative as OpenCV would not provide timestamps which were required in my computer vision algorithm, I found this excellent article https://zulko.github.io/blog/2013/09/27/read-and-write-video-frames-in-python-using-ffmpeg/
  Working up the code on windows I still could’nt get the frame timestamps.
  I recollected seeing on ffmpeg forum somewhere that the video filters like showinfo are bypassed when redirected.

  Here’s what I tried :

  import subprocess as sp
  
  import numpy
  
  import cv2
  
  
  
  command = [ 'ffmpeg', 
  
              '-i', 'e:\sample.wmv',
  
              '-pix_fmt', 'rgb24',
  
              '-vcodec', 'rawvideo',
  
              '-vf', 'showinfo', # video filter - showinfo will provide frame timestamps
  
              '-an','-sn', #-an, -sn disables audio and sub-title processing respectively
  
              '-f', 'image2pipe', '-'] # we need to output to a pipe
  
  
  
  pipe = sp.Popen(command, stdout = sp.PIPE, stderr = sp.STDOUT) # TODO someone on ffmpeg forum said video filters (e.g. showinfo) are bypassed when stdout is redirected to pipes??? 
  
  
  
  for i in range(10):
  
      raw_image = pipe.stdout.read(1280*720*3)
  
      img_info = pipe.stdout.read(244) # 244 characters is the current output of showinfo video filter
  
      print "showinfo output", img_info
  
      image1 =  numpy.fromstring(raw_image, dtype='uint8')
  
      image2 = image1.reshape((720,1280,3))  
  
  
  
      # write video frame to file just to verify
  
      videoFrameName = 'Video_Frame{0}.png'.format(i)
  
      cv2.imwrite(videoFrameName,image2)
  
  
  
      # throw away the data in the pipe's buffer.
  
      pipe.stdout.flush()

  So how to still get the frame timestamps from ffmpeg into python code so that it can be used in my computer vision algorithm ...

• Run python ffmpeg audio convertion code file from subprocess.call() within a flask server

  11 novembre 2019, par Kasun

  I have build a small flask server to handle the request. I have 3 parameters in the api function that i want to get. those are type, user_id, audio_file, One is a file. Since it’s used for the audio file conversion. I have to get a file.. I have tested with this in Postman audio file get saved but the subprocess.call(command) in the api function doesn’t work..

  this is the flask server code

  @app.route('/voice', methods=['GET','POST'])
  
  def process_audio():
  
   try:
  
      if request.method == 'POST':
  
          input_type = request.form['type']
  
          user_id = request.form['user_id']
  
          static_file = request.files['audio_file']
  
          audio_name = secure_filename(static_file.filename)
  
          path = 't/'
  
          status = static_file.save(path + audio_name)
  
          full_file = path + audio_name
  
          if input_type == 1:
  
              cmd = "python t/convert_english.py --audio " + full_file
  
              res = subprocess.call([cmd],shell=True)
  
              f = open('t/ress.txt', 'w')
  
              f.write(str(res))
  
              f.close()
  
              return "true"
  
          else:
  
              cmd = "python t/convert_sinhala.py --audio " + full_file
  
              os.system(cmd)
  
              return "true"
  
      else:
  
          return "false"
  
  
  
  except Exception as e:
  
      print(e)
  
      logger.error(e)
  
      return e

  The audio file get saved in the directory as expected..

  this is the convert_english.py

  import subprocess
  
  import argparse
  
  import os
  
  import logging
  
  import speech_recognition as sr
  
  from tqdm import tqdm
  
  from multiprocessing.dummy import Pool
  
  
  
  #subprocess.call('pip install pydub',shell=True)
  
  
  
  from os import path
  
  from pydub import AudioSegment
  
  
  
  logging.basicConfig(filename='/var/www/img-p/t/ee.log', level=logging.DEBUG, 
  
                      format='%(asctime)s %(levelname)s %(name)s %(message)s')
  
  logger=logging.getLogger(__name__)
  
  
  
  ap = argparse.ArgumentParser()
  
  ap.add_argument("-a", "--audio", required=True,
  
      help="path to input audio file")
  
  args = vars(ap.parse_args())
  
  
  
  src = args["audio"]
  
  dst = "audio.wav"
  
  
  
  sound = AudioSegment.from_mp3(src)
  
  sound.export(dst, format="wav")
  
  
  
  #subprocess.call('pip install ffmpeg-python',shell=True)
  
  
  
  subprocess.call('mkdir parts',shell=True)
  
  
  
  subprocess.call('ffmpeg -i audio.wav -f segment -segment_time 30 -c copy parts/out%09d.wav',shell=True)
  
  
  
  #subprocess.call('pip install SpeechRecognition',shell=True)
  
  
  
  
  
  pool = Pool(8) # Number of concurrent threads
  
  
  
  with open("api-key.json") as f:
  
      GOOGLE_CLOUD_SPEECH_CREDENTIALS = f.read()
  
  
  
  r = sr.Recognizer()
  
  files = sorted(os.listdir('parts/'))
  
  
  
  def transcribe(data):
  
      idx, file = data
  
      name = "parts/" + file
  
      print(name + " started")
  
      # Load audio file
  
      with sr.AudioFile(name) as source:
  
          audio = r.record(source)
  
      # Transcribe audio file
  
      text = r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS)
  
      print(name + " done")
  
      return {
  
          "idx": idx,
  
          "text": text
  
      }
  
  
  
  all_text = pool.map(transcribe, enumerate(files))
  
  pool.close()
  
  pool.join()
  
  
  
  transcript = ""
  
  for t in sorted(all_text, key=lambda x: x['idx']):
  
      total_seconds = t['idx'] * 30
  
      # Cool shortcut from:
  
      # https://stackoverflow.com/questions/775049/python-time-seconds-to-hms
  
      # to get hours, minutes and seconds
  
      m, s = divmod(total_seconds, 60)
  
      h, m = divmod(m, 60)
  
  
  
      # Format time as h:m:s - 30 seconds of text
  
      transcript = transcript + "{:0>2d}:{:0>2d}:{:0>2d} {}\n".format(h, m, s, t['text'])
  
  
  
  print(transcript)
  
  
  
  with open("transcript.txt", "w") as f:
  
      f.write(transcript)
  
  
  
  f = open("transcript.txt")
  
  lines = f.readlines()
  
  f.close()
  
  f = open("transcript.txt", "w", encoding="utf-8")
  
  for line in lines:
  
      f.write(line[8:])
  
  f.close()

  The thing is above code works when i manually run the command -> python t/convert_english.py —audio t/tttttttttt.mp3 like this in the terminal..

  But when i try to run from the flask server itself it doesn’t works.. And I’m not getting an error either.

• Problem playing a sound with pydub Error : pydub.exceptions.CouldntDecodeError : Decoding failed. ffmpeg returned error code : 1

  28 mai 2020, par studioDKR

  I have a problem getting a file played in the browser with pydub. I think the function is working, but I just don't get the right file path to it, or something else is missing. Would love to get your help !

  



  I get the pydob error message : pydub.exceptions.CouldntDecodeError : Decoding failed. ffmpeg returned error code : 1

  



  Here is the error I get :

  



  [2020-05-28 16:04:33,023] ERROR in app: Exception on /overview [POST]
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/app.py", line 2447, in wsgi_app
    response = self.full_dispatch_request()
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/app.py", line 1952, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/app.py", line 1821, in handle_user_exception
    reraise(exc_type, exc_value, tb)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/_compat.py", line 39, in reraise
    raise value
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/app.py", line 1950, in full_dispatch_request
    rv = self.dispatch_request()
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/flask/app.py", line 1936, in dispatch_request
    return self.view_functions[rule.endpoint](**req.view_args)
  File "/Users/Micha/Documents/GitHub/podprod/app.py", line 109, in overview
    sound = AudioSegment.from_file(filepath)
  File "/Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/pydub/audio_segment.py", line 723, in from_file
    raise CouldntDecodeError(
pydub.exceptions.CouldntDecodeError: Decoding failed. ffmpeg returned error code: 1

Output from ffmpeg/avlib:

b'ffmpeg version 4.2.3 Copyright (c) 2000-2020 the FFmpeg developers\n  built with Apple clang version 11.0.3 (clang-1103.0.32.59)\n  configuration: --prefix=/usr/local/Cellar/ffmpeg/4.2.3 --enable-shared --enable-pthreads --enable-version3 --enable-avresample --cc=clang --host-cflags=-fno-stack-check --host-ldflags= --enable-ffplay --enable-gnutls --enable-gpl --enable-libaom --enable-libbluray --enable-libdav1d --enable-libmp3lame --enable-libopus --enable-librubberband --enable-libsnappy --enable-libsrt --enable-libtesseract --enable-libtheora --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxvid --enable-lzma --enable-libfontconfig --enable-libfreetype --enable-frei0r --enable-libass --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-librtmp --enable-libspeex --enable-libsoxr --enable-videotoolbox --disable-libjack --disable-indev=jack\n  libavutil      56. 31.100 / 56. 31.100\n  libavcodec     58. 54.100 / 58. 54.100\n  libavformat    58. 29.100 / 58. 29.100\n  libavdevice    58.  8.100 / 58.  8.100\n  libavfilter     7. 57.100 /  7. 57.100\n  libavresample   4.  0.  0 /  4.  0.  0\n  libswscale      5.  5.100 /  5.  5.100\n  libswresample   3.  5.100 /  3.  5.100\n  libpostproc    55.  5.100 / 55.  5.100\n/Users/Micha/documents/github/podprod/uploads/test2.wav: Invalid data found when processing input\n'


  



  This is the Flask route with the function I am writing.

  



  @app.route("/overview", methods=["GET", "POST"])
def overview():

    entries = []

    # Open a file
    path = app.config["FILE_UPLOADS"]

    with os.scandir(path) as dirs:
        for entry in dirs:
            entries.append(entry.name)

    if request.method == "POST":
        filename = request.form['filename']

        filepath = os.path.join(app.config["FILE_UPLOADS"], filename)

        # Play the sound
        sound = AudioSegment.from_file(filepath)
        play(sound)

        return render_template('overview.html', entries=entries)


  



  Here is the HTML template :

  



      {% extends &#x27;main_template.html&#x27; %}&#xA;&#xA;    {% block title %}PodProd Podcast Overview{% endblock %}&#xA;&#xA;    {% block main %}&#xA;&#xA;    <div class="container">&#xA;&#xA;        <h1>Here is an overview of your files</h1>&#xA;&#xA;        <table class="table table-striped">&#xA;            <tr>&#xA;                <th>Filename</th>&#xA;                <th>Action</th>&#xA;            </tr>&#xA;        {% for result in entries %}&#xA;            {% if ".wav" in result %}&#xA;                <tr>&#xA;                    <td>{{ result }}</td>&#xA;                    <td><form action="" method="POST"> <button type="submit" class="btn btn-primary" value="{{" result="result">Play</button></form>&#xA;                </td></tr>&#xA;            {% endif %}&#xA;        {% endfor %}&#xA;        </table>&#xA;&#xA;    </div>&#xA;&#xA;    {% endblock %}&#xA;