Recherche avancée

Sur d’autres sites (9662)

• Improving Google Cloud Speech-to-Text accuracy

  6 juillet 2020, par lr_optim

  I'm working on a project where I need to perform these steps :

  


  

  1. Record a voice call (.webm -file)

  


  2. Split the webm -file into chunks with ffmpeg and convert the file into wav

  


  3. Transcribe the chunks using SpeechRecognition -library and Google Cloud API

  


  


  I've faced problems with the transcription accuracy and wondering if there is something I could do to improve it. At the time I'm splitting the original file into 30s chunks. I thought there might be one problem, that I might be missing words because of splitting so I've tried also with longer chunks under 60s but didn't notice any improve in accuracy.
Reading trough the speechRecognition docs I decided to set r.energy_threshold = 4000, I also tried to set the energy_treshold dynamically like this :

  


  with sr.AudioFile(name) as source:
    r.dynamic_energy_threshold = True
    r.adjust_for_ambient_noise(source, duration = 1)
    audio = r.record(source)


  


  I've also tested en-US and en-GB to see if there's some difference but there isn't as much as I'd want. The program is supposed to work with english language spoken by nordic people. If someone has experience about choosing a right language model for people speaking with accent, please let me know.

  


  This is the ffmpeg command is use to split the webm file into chunks : command = ['ffmpeg', '-i', filename, '-f', 'segment', '-segment_time', '30', parts_dir + outputname + '%09d.wav']

  


  Is there somethig I could do better ? I'm wondering if the quality is not good enough an Google is having hard time because of that ?

  


  The main problem is I'm getting bad results (lots of wrong words) from Google and wondering if there is something I could do about it.

  


• VideoCapture always returns False in Python OPENCV [Linux]

  7 avril 2017, par Daniyal Shahrokhian

  Every time that I use VideoCapture trying to access the frames from a video file, the return value (ret) is false. See the sample code below :

  cap = cv2.VideoCapture('asd.mkv')
  
      vid = []
  
      while True:
  
          ret, img = cap.read()
  
          if not ret: # Always happens
  
              break
  
          vid.append(cv2.resize(img, (171, 128)))

  I have already tried absolutely everything I could find today by googling, including the OpenCV guide and this long issue on Github. Also, I read some solutions involving moving ffmpeg dll files, but that only was in the case of Windows.

  Any ideas ? Because I defenitely ran out of them.

• VideoCapture always returns False in Python OPENCV [Linux]

  26 octobre 2017, par Daniyal Shahrokhian

  Every time that I use VideoCapture trying to access the frames from a video file, the return value (ret) is false. See the sample code below :

  cap = cv2.VideoCapture('asd.mkv')
  
      vid = []
  
      while True:
  
          ret, img = cap.read()
  
          if not ret: # Always happens
  
              break
  
          vid.append(cv2.resize(img, (171, 128)))

  I have already tried absolutely everything I could find today by googling, including the OpenCV guide and this long issue on Github. Also, I read some solutions involving moving ffmpeg dll files, but that only was in the case of Windows.

  Any ideas ? Because I defenitely ran out of them.