Recherche avancée

Sur d’autres sites (6269)

• moviepy VideoFileClip IndexError : list index out of range, OSError : MoviePy error : failed to read the duration of file

  21 mai 2022, par Mohamed Medhat

  We are recording videos from the browser with the following encoding
'video/webm ; codecs="vp8, opus"', then we upload these videos to an AWS S3 bucket.
Our ML model works on these videos, and one of the models needs to extarct the audio and process it.
Here is a code snapit for extracting the audio

  


  import speech_recognition as sr
import moviepy.editor as me
from denoise2 import denoise
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import math

model_name = 'bert-base-nli-mean-tokens'
model = SentenceTransformer(model_name)


class recomm:
    y = 0.0

    def __init__(self, path, keywords):
        video_clip = me.VideoFileClip(r"{}".format(path))
        path2 = "y2.wav"
        video_clip.audio.write_audiofile(r"{}".format(path2), nbytes=2)
        recognizer = sr.Recognizer()
        """a = AudioSegment.from_wav(path2)
        a = a + 5
        a.export(path2, "wav")"""
        audio_clip = sr.AudioFile("{}".format(path2))
        with audio_clip as source:
            audio_file = recognizer.record(source)
        sent = []
        result = ""
        try:
            result = recognizer.recognize_google(audio_file)
        except sr.UnknownValueError:
            print("Can not process audio ")
        if not result:
            self.y = 0
        else:
            print(result)
            sent.append(result)
            sent = sent + keywords
            sent_vec3 = model.encode(sent)
            x = cosine_similarity(
                [sent_vec3[0]],
                sent_vec3[1:]
            )
            for i in range(len(x)):
                self.y = self.y + x[0][i]
            self.y = (self.y / (len(sent) - 1)) * 1000.0

    def res(self):
        if self.y < 0:
            self.y = 0
        return self.y


  


  And that's the traceback,
the error occurred at this line

  


  video_clip = me.VideoFileClip(r"{}".format(path))


  


  Traceback (most recent call last):
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/moviepy/video/io/ffmpeg_reader.py", line 286, in ffmpeg_parse_infos
match = re.findall("([0-9][0-9]:[0-9][0-9]:[0-9][0-9].[0-9][0-9])", line)[0]
IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "main.py", line 90, in
main()
File "main.py", line 85, in main
interviews_channel.start_consuming()
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/pika/adapters/blocking_connection.py", line 1865, in start_consuming
self._process_data_events(time_limit=None)
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/pika/adapters/blocking_connection.py", line 2026, in _process_data_events
self.connection.process_data_events(time_limit=time_limit)
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/pika/adapters/blocking_connection.py", line 833, in process_data_events
self._dispatch_channel_events()
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/pika/adapters/blocking_connection.py", line 567, in _dispatch_channel_events
impl_channel._get_cookie()._dispatch_events()
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/pika/adapters/blocking_connection.py", line 1492, in _dispatch_events
consumer_info.on_message_callback(self, evt.method,
File "main.py", line 79, in callback
processing(json.loads(body))
File "main.py", line 34, in processing
r = recomm(path, keywords)
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/recommendation.py", line 17, in init
video_clip = me.VideoFileClip(r"{}".format(path))
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/moviepy/video/io/VideoFileClip.py", line 88, in init
self.reader = FFMPEG_VideoReader(filename, pix_fmt=pix_fmt,
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/moviepy/video/io/ffmpeg_reader.py", line 35, in init
infos = ffmpeg_parse_infos(filename, print_infos, check_duration,
File "/home/medo/Dev/Smart-remotely-interviewing-system/backend/Process-interview/test/lib/python3.8/site-packages/moviepy/video/io/ffmpeg_reader.py", line 289, in ffmpeg_parse_infos
raise IOError(("MoviePy error: failed to read the duration of file %s.\n"
OSError: MoviePy error: failed to read the duration of file 74b74292-3642-486a-8319-255bb7e7da5a-1647363285285.webm.
Here are the file infos returned by ffmpeg:

ffmpeg version 4.2.2-static https://johnvansickle.com/ffmpeg/ Copyright (c) 2000-2019 the FFmpeg developers
built with gcc 8 (Debian 8.3.0-6)
configuration: --enable-gpl --enable-version3 --enable-static --disable-debug --disable-ffplay --disable-indev=sndio --disable-outdev=sndio --cc=gcc --enable-fontconfig --enable-frei0r --enable-gnutls --enable-gmp --enable-libgme --enable-gray --enable-libaom --enable-libfribidi --enable-libass --enable-libvmaf --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-librubberband --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libvorbis --enable-libopus --enable-libtheora --enable-libvidstab --enable-libvo-amrwbenc --enable-libvpx --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libdav1d --enable-libxvid --enable-libzvbi --enable-libzimg
libavutil 56. 31.100 / 56. 31.100
libavcodec 58. 54.100 / 58. 54.100
libavformat 58. 29.100 / 58. 29.100
libavdevice 58. 8.100 / 58. 8.100
libavfilter 7. 57.100 / 7. 57.100
libswscale 5. 5.100 / 5. 5.100
libswresample 3. 5.100 / 3. 5.100
libpostproc 55. 5.100 / 55. 5.100
Input #0, matroska,webm, from '74b74292-3642-486a-8319-255bb7e7da5a-1647363285285.webm':
Metadata:
encoder : Chrome
Duration: N/A, start: 0.000000, bitrate: N/A
Stream #0:0(eng): Audio: opus, 48000 Hz, mono, fltp (default)
Stream #0:1(eng): Video: vp8, yuv420p(progressive), 640x480, SAR 1:1 DAR 4:3, 29.42 fps, 29.42 tbr, 1k tbn, 1k tbc (default)
Metadata:
alpha_mode : 1
At least one output file must be specified


  


• Error with IO.popen and ffmepg

  6 mars 2015, par Florian Dano Clement

  I received files in mp3 (2 minutes/files) I want to concatenate together and create a bigger file. So I created my model a function to do this using ffmpeg and IO.popen

  FileUtils.mkdir_p "#{Rails.root}/tmp/files"
  
  imported_dir = "#{Rails.root}/tmp/files/#{SecureRandom.uuid}"
  
  links.each_with_index do |link, index|
  
    file_path = "#{imported_dir}_#{index}#{File.extname(link)}"
  
    File.open(file_path, 'wb') do |file|
  
      file.write open(link).read
  
    end
  
    concat_list << "file '#{file_path}'\n"
  
  end
  
  File.open("#{imported_dir}.txt", 'w'){ |f| f.write(concat_list)}
  
  io = IO.popen("#{Rails.root}/lib/ffmpeg/ffmpeg -f concat -i #{imported_dir}.txt -c copy #{imported_dir}.mp3").readlines
  
  if sound = Sound.create(user_id: user.id, file: File.open("#{imported_dir}.mp3"), lang: lang, title: title)
  
    audio = FFMPEG::Movie.new("#{imported_dir}.mp3")
  
    if !audio.valid?
  
      puts "//_!_\\\\ Failed reading with ffmpeg (#{sound.id})#{sound.title} //_!_\\\\"
  
      return false
  
    end
  
  end 

  the problem is that my .txt file containing the file path

  file '/home/test/apps/example/releases/20150305224026/tmp/files/4dbe9707-cfef-467b-ab2c-a5e1e1165953_0.mp3'

  created files as well but the final file is not created and i got the error message :

  No such file or directory @ rb_sysopen - /home/test/apps/example/releases/20150305224026/tmp/files/4dbe9707-cfef-467b-ab2c-a5e1e1165953.mp3

  If anyone could help me

• how to add header info to a wav file to get a same result as ffmpeg ?

  30 avril 2023, par Q.Tong

  I'm trying to generate a .wav file with Fastspeech. When I save the data as .pcm file, and transfer it to .wav by ffmpeg, it works well.But when I just add a wav header info and save it into .wav, it sounds very noisy, What's wrong with my code ?

  


  code for pcm :

  


      wav = wav.astype(np.float32)
    wav = wav.tostring()
    with open('test.pcm', 'wb') as f:
        f.write(wav)


  


  ffmpeg command :

  


  ffmpeg -f f32le -ar 16000 -i test.pcm file.wav  # works well


  


  write wav straightly :

  


  import struct

def pcm2wav(sample_rate, pcm_voice):
    if pcm_voice.startswith("RIFF".encode()):
        return pcm_voice
    else:
        sampleNum = len(pcm_voice)
        rHeaderInfo = "RIFF".encode()
        rHeaderInfo += struct.pack('i', sampleNum + 44)
        rHeaderInfo += 'WAVEfmt '.encode()
        rHeaderInfo += struct.pack('i', 16)
        rHeaderInfo += struct.pack('h', 1)
        rHeaderInfo += struct.pack('h', 1)
        rHeaderInfo += struct.pack('i', sample_rate)
        rHeaderInfo += struct.pack('i', sample_rate * int(32 / 8))
        rHeaderInfo += struct.pack("h", int(32 / 8))
        rHeaderInfo += struct.pack("h", 32)
        rHeaderInfo += "data".encode()
        rHeaderInfo += struct.pack('i', sampleNum)
        rHeaderInfo += pcm_voice
        return rHeaderInfo

# .......
# get data with FastSpeech model
wav = wav.astype(np.float32)
wav = wav.tostring()
wav = pcm2wav(16000, wav)
with open('test.wav', 'wb') as f:
    f.write(wav)   # many noisy sounds