Recherche avancée

Sur d’autres sites (8841)

• 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.

• FFmpeg overlay positioning issue : Converting frontend center coordinates to FFmpeg top-left coordinates

  25 janvier, par tarun

  I'm building a web-based video editor where users can :

  


  Add multiple videos
Add images
Add text overlays with background color

  


  Frontend sends coordinates where each element's (x,y) represents its center position.
on click of the export button i want all data to be exported as one final video
on click i send the data to the backend like -

  


   const exportAllVideos = async () => {
    try {
      const formData = new FormData();
        
      
      const normalizedVideos = videos.map(video => ({
          ...video,
          startTime: parseFloat(video.startTime),
          endTime: parseFloat(video.endTime),
          duration: parseFloat(video.duration)
      })).sort((a, b) => a.startTime - b.startTime);

      
      for (const video of normalizedVideos) {
          const response = await fetch(video.src);
          const blobData = await response.blob();
          const file = new File([blobData], `${video.id}.mp4`, { type: "video/mp4" });
          formData.append("videos", file);
      }

      
      const normalizedImages = images.map(image => ({
          ...image,
          startTime: parseFloat(image.startTime),
          endTime: parseFloat(image.endTime),
          x: parseInt(image.x),
          y: parseInt(image.y),
          width: parseInt(image.width),
          height: parseInt(image.height),
          opacity: parseInt(image.opacity)
      }));

      
      for (const image of normalizedImages) {
          const response = await fetch(image.src);
          const blobData = await response.blob();
          const file = new File([blobData], `${image.id}.png`, { type: "image/png" });
          formData.append("images", file);
      }

      
      const normalizedTexts = texts.map(text => ({
          ...text,
          startTime: parseFloat(text.startTime),
          endTime: parseFloat(text.endTime),
          x: parseInt(text.x),
          y: parseInt(text.y),
          fontSize: parseInt(text.fontSize),
          opacity: parseInt(text.opacity)
      }));

      
      formData.append("metadata", JSON.stringify({
          videos: normalizedVideos,
          images: normalizedImages,
          texts: normalizedTexts
      }));

      const response = await fetch("my_flask_endpoint", {
          method: "POST",
          body: formData
      });

      if (!response.ok) {
        
          console.log('wtf', response);
          
      }

      const finalVideo = await response.blob();
      const url = URL.createObjectURL(finalVideo);
      const a = document.createElement("a");
      a.href = url;
      a.download = "final_video.mp4";
      a.click();
      URL.revokeObjectURL(url);

    } catch (e) {
      console.log(e, "err");
    }
  };


  


  the frontend data for each object that is text image and video we are storing it as an array of objects below is the Data strcutre for each object -

  


  // the frontend data for each
  const newVideo = {
      id: uuidv4(),
      src: URL.createObjectURL(videoData.videoBlob),
      originalDuration: videoData.duration,
      duration: videoData.duration,
      startTime: 0,
      playbackOffset: 0,
      endTime: videoData.endTime || videoData.duration,
      isPlaying: false,
      isDragging: false,
      speed: 1,
      volume: 100,
      x: window.innerHeight / 2,
      y: window.innerHeight / 2,
      width: videoData.width,
      height: videoData.height,
    };
    const newTextObject = {
      id: uuidv4(),
      description: text,
      opacity: 100,
      x: containerWidth.width / 2,
      y: containerWidth.height / 2,
      fontSize: 18,
      duration: 20,
      endTime: 20,
      startTime: 0,
      color: "#ffffff",
      backgroundColor: hasBG,
      padding: 8,
      fontWeight: "normal",
      width: 200,
      height: 40,
    };

    const newImage = {
      id: uuidv4(),
      src: URL.createObjectURL(imageData),
      x: containerWidth.width / 2,
      y: containerWidth.height / 2,
      width: 200,
      height: 200,
      borderRadius: 0,
      startTime: 0,
      endTime: 20,
      duration: 20,
      opacity: 100,
    };



  


  BACKEND CODE -

  


  import os
import shutil
import subprocess
from flask import Flask, request, send_file
import ffmpeg
import json
from werkzeug.utils import secure_filename
import uuid
from flask_cors import CORS


app = Flask(__name__)
CORS(app, resources={r"/*": {"origins": "*"}})



UPLOAD_FOLDER = 'temp_uploads'
if not os.path.exists(UPLOAD_FOLDER):
    os.makedirs(UPLOAD_FOLDER)


@app.route('/')
def home():
    return 'Hello World'


OUTPUT_WIDTH = 1920
OUTPUT_HEIGHT = 1080



@app.route('/process', methods=['POST'])
def process_video():
    work_dir = None
    try:
        work_dir = os.path.abspath(os.path.join(UPLOAD_FOLDER, str(uuid.uuid4())))
        os.makedirs(work_dir)
        print(f"Created working directory: {work_dir}")

        metadata = json.loads(request.form['metadata'])
        print("Received metadata:", json.dumps(metadata, indent=2))
        
        video_paths = []
        videos = request.files.getlist('videos')
        for idx, video in enumerate(videos):
            filename = f"video_{idx}.mp4"
            filepath = os.path.join(work_dir, filename)
            video.save(filepath)
            if os.path.exists(filepath) and os.path.getsize(filepath) > 0:
                video_paths.append(filepath)
                print(f"Saved video to: {filepath} Size: {os.path.getsize(filepath)}")
            else:
                raise Exception(f"Failed to save video {idx}")

        image_paths = []
        images = request.files.getlist('images')
        for idx, image in enumerate(images):
            filename = f"image_{idx}.png"
            filepath = os.path.join(work_dir, filename)
            image.save(filepath)
            if os.path.exists(filepath):
                image_paths.append(filepath)
                print(f"Saved image to: {filepath}")

        output_path = os.path.join(work_dir, 'output.mp4')

        filter_parts = []

        base_duration = metadata["videos"][0]["duration"] if metadata["videos"] else 10
        filter_parts.append(f'color=c=black:s={OUTPUT_WIDTH}x{OUTPUT_HEIGHT}:d={base_duration}[canvas];')

        for idx, (path, meta) in enumerate(zip(video_paths, metadata['videos'])):
            x_pos = int(meta.get("x", 0) - (meta.get("width", 0) / 2))
            y_pos = int(meta.get("y", 0) - (meta.get("height", 0) / 2))
            
            filter_parts.extend([
                f'[{idx}:v]setpts=PTS-STARTPTS,scale={meta.get("width", -1)}:{meta.get("height", -1)}[v{idx}];',
                f'[{idx}:a]asetpts=PTS-STARTPTS[a{idx}];'
            ])

            if idx == 0:
                filter_parts.append(
                    f'[canvas][v{idx}]overlay=x={x_pos}:y={y_pos}:eval=init[temp{idx}];'
                )
            else:
                filter_parts.append(
                    f'[temp{idx-1}][v{idx}]overlay=x={x_pos}:y={y_pos}:'
                    f'enable=\'between(t,{meta["startTime"]},{meta["endTime"]})\':eval=init'
                    f'[temp{idx}];'
                )

        last_video_temp = f'temp{len(video_paths)-1}'

        if video_paths:
            audio_mix_parts = []
            for idx in range(len(video_paths)):
                audio_mix_parts.append(f'[a{idx}]')
            filter_parts.append(f'{"".join(audio_mix_parts)}amix=inputs={len(video_paths)}[aout];')

        
        if image_paths:
            for idx, (img_path, img_meta) in enumerate(zip(image_paths, metadata['images'])):
                input_idx = len(video_paths) + idx
                
                
                x_pos = int(img_meta["x"] - (img_meta["width"] / 2))
                y_pos = int(img_meta["y"] - (img_meta["height"] / 2))
                
                filter_parts.extend([
                    f'[{input_idx}:v]scale={img_meta["width"]}:{img_meta["height"]}[img{idx}];',
                    f'[{last_video_temp}][img{idx}]overlay=x={x_pos}:y={y_pos}:'
                    f'enable=\'between(t,{img_meta["startTime"]},{img_meta["endTime"]})\':'
                    f'alpha={img_meta["opacity"]/100}[imgout{idx}];'
                ])
                last_video_temp = f'imgout{idx}'

        if metadata.get('texts'):
            for idx, text in enumerate(metadata['texts']):
                next_output = f'text{idx}' if idx < len(metadata['texts']) - 1 else 'vout'
                
                escaped_text = text["description"].replace("'", "\\'")
                
                x_pos = int(text["x"] - (text["width"] / 2))
                y_pos = int(text["y"] - (text["height"] / 2))
                
                text_filter = (
                    f'[{last_video_temp}]drawtext=text=\'{escaped_text}\':'
                    f'x={x_pos}:y={y_pos}:'
                    f'fontsize={text["fontSize"]}:'
                    f'fontcolor={text["color"]}'
                )
                
                if text.get('backgroundColor'):
                    text_filter += f':box=1:boxcolor={text["backgroundColor"]}:boxborderw=5'
                
                if text.get('fontWeight') == 'bold':
                    text_filter += ':font=Arial-Bold'
                
                text_filter += (
                    f':enable=\'between(t,{text["startTime"]},{text["endTime"]})\''
                    f'[{next_output}];'
                )
                
                filter_parts.append(text_filter)
                last_video_temp = next_output
        else:
            filter_parts.append(f'[{last_video_temp}]null[vout];')

        
        filter_complex = ''.join(filter_parts)

        
        cmd = [
            'ffmpeg',
            *sum([['-i', path] for path in video_paths], []),
            *sum([['-i', path] for path in image_paths], []),
            '-filter_complex', filter_complex,
            '-map', '[vout]'
        ]
        
        
        if video_paths:
            cmd.extend(['-map', '[aout]'])
        
        cmd.extend(['-y', output_path])

        print(f"Running ffmpeg command: {' '.join(cmd)}")
        result = subprocess.run(cmd, capture_output=True, text=True)
        
        if result.returncode != 0:
            print(f"FFmpeg error output: {result.stderr}")
            raise Exception(f"FFmpeg processing failed: {result.stderr}")

        return send_file(
            output_path,
            mimetype='video/mp4',
            as_attachment=True,
            download_name='final_video.mp4'
        )

    except Exception as e:
        print(f"Error in video processing: {str(e)}")
        return {'error': str(e)}, 500
    
    finally:
        if work_dir and os.path.exists(work_dir):
            try:
                print(f"Directory contents before cleanup: {os.listdir(work_dir)}")
                if not os.environ.get('FLASK_DEBUG'):
                    shutil.rmtree(work_dir)
                else:
                    print(f"Keeping directory for debugging: {work_dir}")
            except Exception as e:
                print(f"Cleanup error: {str(e)}")

                
if __name__ == '__main__':
    app.run(debug=True, port=8000)



  


  I'm also attaching what the final thing looks like on the frontend web vs in the downloaded video
and as u can see the downloaded video has all coords and positions messed up be it of the texts, images as well as videos


  


  can somebody please help me figure this out :)

  


• FFmpeg - MJPEG decoding gives inconsistent values

  28 décembre 2016, par ahmadh

  I have a set of JPEG frames which I am muxing into an avi, which gives me a mjpeg video. This is the command I run on the console :

  ffmpeg -y -start_number 0 -i %06d.JPEG -codec copy vid.avi

  When I try to demux the video using ffmpeg C api, I get frames which are slightly different in values. Demuxing code looks something like this :

  AVFormatContext* fmt_ctx = NULL;
  
  AVCodecContext* cdc_ctx = NULL;
  
  AVCodec* vid_cdc = NULL;
  
  int ret;
  
  unsigned int height, width;
  
  
  
  ....
  
  // read_nframes is the number of frames to read
  
  output_arr = new unsigned char [height * width * 3 * 
  
                                  sizeof(unsigned char) * read_nframes];
  
  
  
  avcodec_open2(cdc_ctx, vid_cdc, NULL);
  
  
  
  int num_bytes;
  
  uint8_t* buffer = NULL;
  
  const AVPixelFormat out_format = AV_PIX_FMT_RGB24;
  
  
  
  num_bytes = av_image_get_buffer_size(out_format, width, height, 1);
  
  buffer = (uint8_t*)av_malloc(num_bytes * sizeof(uint8_t));
  
  
  
  AVFrame* vid_frame = NULL;
  
  vid_frame = av_frame_alloc();
  
  AVFrame* conv_frame = NULL;
  
  conv_frame = av_frame_alloc();
  
  
  
  av_image_fill_arrays(conv_frame->data, conv_frame->linesize, buffer, 
  
                       out_format, width, height, 1);
  
  
  
  struct SwsContext *sws_ctx = NULL;
  
  sws_ctx = sws_getContext(width, height, cdc_ctx->pix_fmt,
  
                           width, height, out_format,
  
                           SWS_BILINEAR, NULL,NULL,NULL);
  
  
  
  int frame_num = 0;
  
  AVPacket vid_pckt;
  
  while (av_read_frame(fmt_ctx, &vid_pckt) >=0) {
  
      ret = avcodec_send_packet(cdc_ctx, &vid_pckt);
  
      if (ret < 0)
  
          break;
  
  
  
      ret = avcodec_receive_frame(cdc_ctx, vid_frame);
  
      if (ret < 0 && ret != AVERROR(EAGAIN) && ret != AVERROR_EOF)
  
          break;
  
      if (ret >= 0) {
  
          // convert image from native format to planar GBR
  
          sws_scale(sws_ctx, vid_frame->data, 
  
                    vid_frame->linesize, 0, vid_frame->height, 
  
                    conv_frame->data, conv_frame->linesize);
  
  
  
          unsigned char* r_ptr = output_arr + 
  
              (height * width * sizeof(unsigned char) * 3 * frame_num);
  
          unsigned char* g_ptr = r_ptr + (height * width * sizeof(unsigned char));
  
          unsigned char* b_ptr = g_ptr + (height * width * sizeof(unsigned char));
  
          unsigned int pxl_i = 0;
  
  
  
          for (unsigned int r = 0; r < height; ++r) {
  
              uint8_t* avframe_r = conv_frame->data[0] + r*conv_frame->linesize[0];
  
              for (unsigned int c = 0; c < width; ++c) {
  
                  r_ptr[pxl_i] = avframe_r[0];
  
                  g_ptr[pxl_i]   = avframe_r[1];
  
                  b_ptr[pxl_i]   = avframe_r[2];
  
                  avframe_r += 3;
  
                  ++pxl_i;
  
              }
  
          }
  
  
  
          ++frame_num;
  
  
  
          if (frame_num >= read_nframes)
  
              break;
  
      }
  
  }
  
  
  
  ...

  In my experience around two-thirds of the pixel values are different, each by +-1 (in a range of [0,255]). I am wondering is it due to some decoding scheme FFmpeg uses for reading JPEG frames ? I tried encoding and decoding png frames, and it works perfectly fine. I am sure this is something to do with the libav decoding process because the MD5 values are consistent between the images and the video :

  ffmpeg -i %06d.JPEG -f framemd5 -
  
  ffmpeg -i vid.avi -f framemd5 -

  In short my goal is to get the same pixel by pixel values for each JPEG frame as I would I have gotten if I was reading the JPEG images directly. Here is the stand-alone bitbucket code I used. It includes cmake files to build code, and a couple of jpeg frames with the converted avi file to test this problem. (give ’—filetype png’ to test the png decoding).