Recherche avancée

Sur d’autres sites (8040)

• 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.

• pydub.exceptions.CouldntDecodeError : Decoding failed. ffmpeg returned error code : 1

  9 avril, par azail765

  This script will work on a 30 second wav file but not a 10 minutes phone call also in wav format. Any help would be appreciated

  


  I've downloaded ffmpeg.

  


  # Import necessary libraries 
from pydub import AudioSegment 
import speech_recognition as sr 
import os
import pydub


chunk_count = 0
directory = os.fsencode(r'C:\Users\zach.blair\Downloads\speechRecognition\New folder')
# Text file to write the recognized audio 
fh = open("recognized.txt", "w+")
for file in os.listdir(directory):
     filename = os.fsdecode(file)
     if filename.endswith(".wav"):
        chunk_count += 1
             # Input audio file to be sliced 
        audio = AudioSegment.from_file(filename,format="wav") 
          
        ''' 
        Step #1 - Slicing the audio file into smaller chunks. 
        '''
        # Length of the audiofile in milliseconds 
        n = len(audio) 
          
        # Variable to count the number of sliced chunks 
        counter = 1
          
         
          
        # Interval length at which to slice the audio file. 
        interval = 20 * 1000
          
        # Length of audio to overlap.  
        overlap = 1 * 1000
          
        # Initialize start and end seconds to 0 
        start = 0
        end = 0
          
        # Flag to keep track of end of file. 
        # When audio reaches its end, flag is set to 1 and we break 
        flag = 0
          
        # Iterate from 0 to end of the file, 
        # with increment = interval 
        for i in range(0, 2 * n, interval): 
              
            # During first iteration, 
            # start is 0, end is the interval 
            if i == 0: 
                start = 0
                end = interval 
          
            # All other iterations, 
            # start is the previous end - overlap 
            # end becomes end + interval 
            else: 
                start = end - overlap 
                end = start + interval  
          
            # When end becomes greater than the file length, 
            # end is set to the file length 
            # flag is set to 1 to indicate break. 
            if end >= n: 
                end = n 
                flag = 1
          
            # Storing audio file from the defined start to end 
            chunk = audio[start:end] 
          
            # Filename / Path to store the sliced audio 
            filename = str(chunk_count)+'chunk'+str(counter)+'.wav'
          
            # Store the sliced audio file to the defined path 
            chunk.export(filename, format ="wav") 
            # Print information about the current chunk 
            print(str(chunk_count)+str(counter)+". Start = "
                                +str(start)+" end = "+str(end)) 
          
            # Increment counter for the next chunk 
            counter = counter + 1
              
          
            AUDIO_FILE = filename 
            
            # Initialize the recognizer 
            r = sr.Recognizer() 
          
            # Traverse the audio file and listen to the audio 
            with sr.AudioFile(AUDIO_FILE) as source: 
                audio_listened = r.listen(source) 
          
            # Try to recognize the listened audio 
            # And catch expections. 
            try:     
                rec = r.recognize_google(audio_listened) 
                  
                # If recognized, write into the file. 
                fh.write(rec+" ") 
              
            # If google could not understand the audio 
            except sr.UnknownValueError: 
                    print("Empty Value") 
          
            # If the results cannot be requested from Google. 
            # Probably an internet connection error. 
            except sr.RequestError as e: 
                print("Could not request results.") 
          
            # Check for flag. 
            # If flag is 1, end of the whole audio reached. 
            # Close the file and break.                  
fh.close()    


  


  I get this error on audio = AudioSegment.from_file(filename,format="wav") :

  


  Traceback (most recent call last):&#xA;  File "C:\Users\zach.blair\Downloads\speechRecognition\New folder\speechRecognition3.py", line 17, in <module>&#xA;    audio = AudioSegment.from_file(filename,format="wav")&#xA;  File "C:\Users\zach.blair\AppData\Local\Programs\Python\Python37-32\lib\site-packages\pydub\audio_segment.py", line 704, in from_file&#xA;    p.returncode, p_err))&#xA;pydub.exceptions.CouldntDecodeError: Decoding failed. ffmpeg returned error code: 1&#xA;</module>

  


  Output from ffmpeg/avlib :

  


    ffmpeg version N-95027-g8c90bb8ebb Copyright (c) 2000-2019 the FFmpeg developers
  built with gcc 9.2.1 (GCC) 20190918
  configuration: --enable-gpl --enable-version3 --enable-sdl2 --enable-fontconfig --enable-gnutls --enable-iconv --enable-libass --enable-libdav1d --enable-libbluray --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libtheora --enable-libtwolame --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libzimg --enable-lzma --enable-zlib --enable-gmp --enable-libvidstab --enable-libvorbis --enable-libvo-amrwbenc --enable-libmysofa --enable-libspeex --enable-libxvid --enable-libaom --enable-libmfx --enable-ffnvcodec --enable-cuvid --enable-d3d11va --enable-nvenc --enable-nvdec --enable-dxva2 --enable-avisynth --enable-libopenmpt --enable-amf
  libavutil      56. 35.100 / 56. 35.100
  libavcodec     58. 58.101 / 58. 58.101
  libavformat    58. 33.100 / 58. 33.100
  libavdevice    58.  9.100 / 58.  9.100
  libavfilter     7. 58.102 /  7. 58.102
  libswscale      5.  6.100 /  5.  6.100
  libswresample   3.  6.100 /  3.  6.100
  libpostproc    55.  6.100 / 55.  6.100
Guessed Channel Layout for Input Stream #0.0 : mono
Input #0, wav, from '2a.wav.wav':
  Duration: 00:09:52.95, bitrate: 64 kb/s
    Stream #0:0: Audio: pcm_mulaw ([7][0][0][0] / 0x0007), 8000 Hz, mono, s16, 64 kb/s
Stream mapping:
  Stream #0:0 -> #0:0 (pcm_mulaw (native) -> pcm_s8 (native))
Press [q] to stop, [?] for help
[wav @ 0000024307974400] pcm_s8 codec not supported in WAVE format
Could not write header for output file #0 (incorrect codec parameters ?): Function not implemented
Error initializing output stream 0:0 -- 
Conversion failed!


  


• Is there way to compile ffmpeg in VS 2019 without (1) installing MSYS, (2) using assembler sources ? [duplicate]

  21 octobre 2023, par Tobic

  I want to compile ffmpeg in VS 2019 without installing additional components such as MSYS and assembler sources.
If I understand correctly, I have to install MSYS to do that and I would like not install it.

  


  Can I do it without MSYS - and if it is real, in what way ?
  
I have downloaded ffmpeg sources and the first step to install it - execute a file .\configure (bash script ?) that comes with ffmpeg.