clean_randomsplice.py

'''
               AAA               lllllll lllllll   iiii                      
              A:::A              l:::::l l:::::l  i::::i                     
             A:::::A             l:::::l l:::::l   iiii                      
            A:::::::A            l:::::l l:::::l                             
           A:::::::::A            l::::l  l::::l iiiiiii     eeeeeeeeeeee    
          A:::::A:::::A           l::::l  l::::l i:::::i   ee::::::::::::ee  
         A:::::A A:::::A          l::::l  l::::l  i::::i  e::::::eeeee:::::ee
        A:::::A   A:::::A         l::::l  l::::l  i::::i e::::::e     e:::::e
       A:::::A     A:::::A        l::::l  l::::l  i::::i e:::::::eeeee::::::e
      A:::::AAAAAAAAA:::::A       l::::l  l::::l  i::::i e:::::::::::::::::e 
     A:::::::::::::::::::::A      l::::l  l::::l  i::::i e::::::eeeeeeeeeee  
    A:::::AAAAAAAAAAAAA:::::A     l::::l  l::::l  i::::i e:::::::e           
   A:::::A             A:::::A   l::::::ll::::::li::::::ie::::::::e          
  A:::::A               A:::::A  l::::::ll::::::li::::::i e::::::::eeeeeeee  
 A:::::A                 A:::::A l::::::ll::::::li::::::i  ee:::::::::::::e  
AAAAAAA                   AAAAAAAlllllllllllllllliiiiiiii    eeeeeeeeeeeeee  


/  __ \ |                (_)              / _ \ | ___ \_   _|  _ 
| /  \/ | ___  __ _ _ __  _ _ __   __ _  / /_\ \| |_/ / | |   (_)
| |   | |/ _ \/ _` | '_ \| | '_ \ / _` | |  _  ||  __/  | |      
| \__/\ |  __/ (_| | | | | | | | | (_| | | | | || |    _| |_   _ 
 \____/_|\___|\__,_|_| |_|_|_| |_|\__, | \_| |_/\_|    \___/  (_)
                                   __/ |                         
                                  |___/                          
  ___            _ _       
 / _ \          | (_)      
/ /_\ \_   _  __| |_  ___  
|  _  | | | |/ _` | |/ _ \ 
| | | | |_| | (_| | | (_) |
\_| |_/\__,_|\__,_|_|\___/ 
                                             

This cleaning script converts all audio files in a given folder to 20 seconds in length.

Note you can change this to any arbitary length by changing the desiredlength function below.

This cleaning script is enabled if default_audio_cleaners=['clean_randomsplice'] 
'''
import soundfile as sf 
import os, ffmpy, random, getpass

def clean_randomsplice(audiofile, desiredlength):
        try:
                data, samplerate = sf.read(audiofile)
                totalframes=len(data)
                totalseconds=int(totalframes/samplerate)
                startsec=random.randint(0,totalseconds-(desiredlength+1))
                endsec=startsec+desiredlength
                startframe=samplerate*startsec
                endframe=samplerate*endsec
                
                #write file to resave wave file at those frames
                newfile='snipped_'+audiofile
                sf.write(newfile, data[int(startframe):int(endframe)], samplerate)
                os.remove(audiofile)
                return [newfile]
        except:
                print('error, skipping...')
                return [audiofile]