API tools faq
paste
Advertisement
Guest User

Audacity label tool

a guest
May 20th, 2019
128
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 13.82 KB | None | 0 0
raw download clone embed print report
  1. #! C:\Python\Python37\python.exe
  2. #! coding: utf-8
  3. #! python3
  4. # Black Cat 2019
  5. # Licence cc-by-nc-sa
  6. # Adds timestamp in format HH_MM_SS_ from precise audacity timestamps
  7. # Also, checks for type and abbreviations
  8. # And do a freaking mess of other things
  9.  
  10. import difflib
  11.  
  12. VERSION = 0.9
  13.  
  14. def timestampToTime( timestamp ) :
  15.     hours = int( timestamp/3600 )
  16.     minutes = int( (timestamp - (3600*hours)) / 60 )
  17.     seconds = int( (timestamp - (60*minutes) - (3600*hours)) )
  18.     millis = int( (timestamp - int(timestamp)) * 1000 )
  19.     fractional = timestamp - int(timestamp)
  20.     return (hours, minutes, seconds, millis, fractional)
  21.  
  22.  
  23. def timeToTimestamp( hours=0, minutes=0, seconds=0, millis=0 ) :
  24.     return (3600*hours)+(60*minutes)+seconds+(millis/1000)
  25.    
  26.  
  27.  
  28. def likeness( a="", b="" ) :
  29.     likeness = difflib.SequenceMatcher(None, a, b).ratio()
  30.     return likeness
  31.  
  32. # This is so dirty and lazy. Please, uses a real library like "inflect"
  33. def num2str( num=0 ) :
  34.     string = ""
  35.     if abs( num ) > 9999999999 :
  36.         error( "num2str : (positive or negative) Number to big sorry my coder was lazy" )
  37.         string = str(num)
  38.     elif num == 0 :
  39.         string = "zero"
  40.     else :
  41.         # Power Of Ten = 0
  42.         units = ["", "one", "two", "three", "four", "five", "six", "seven", "eight", "nine", "TEN", "eleven", "twelve", "thirteen", "fourteen", "fifteen", "sixteen", "seventeen", "eighteen", "nineteen"]
  43.         # Power Of Ten = 1
  44.         decades = ["", "ten", "twenty", "thirty", "fourty", "fifty", "sixty", "seventy", "eighty", "ninety"]
  45.         hundreds = "hundred"
  46.         # Power Of Ten [0, 3, 6, 9]
  47.         thousands = ["", "thousand", "million", "billion"]
  48.        
  49.         n = abs(num)
  50.         t = 0
  51.         string = ""
  52.         while n > 0 :
  53.             strHun = ""
  54.             hun = n % 1000
  55.             n = int(n/1000)
  56.            
  57.             u = hun % 10
  58.             d = int((hun % 100)/10)
  59.             c = int(hun/100)
  60.            
  61.             if d < 2 :
  62.                 strHun = units[(10*d)+u]
  63.             else :
  64.                 strHun = decades[d] + " " + units[u]
  65.            
  66.             if c > 0 :
  67.                 strHun = units[c] + " hundred and " + strHun
  68.            
  69.             if t != 0 :
  70.                 strHun = strHun + " " + thousands[t] + ", "
  71.             t += 1
  72.            
  73.             if string != "" :
  74.                 string = " " + string
  75.             string = strHun + string
  76.        
  77.         if num < 0 :
  78.             string = "minus "
  79.        
  80.     return string
  81.  
  82. #==============================================================================
  83. # Eye candy
  84. #==============================================================================
  85. def info( text="?" ) :
  86.     global ERROR_LEVEL
  87.     if ERROR_LEVEL > 2 :
  88.         print( "   info   : "+text )
  89.  
  90. def good( text="?" ) :
  91.     global ERROR_LEVEL
  92.     if ERROR_LEVEL > 1 :
  93.         print( "   good   : "+text )
  94.  
  95. def warning( text="?" ) :
  96.     global ERROR_LEVEL
  97.     if ERROR_LEVEL > 0 :
  98.         print( "[warning] : "+text )
  99.  
  100. def error( text="?" ) :
  101.     print( "[ ERROR ] : "+text )
  102.  
  103. def draw_spacer(char="=") :
  104.     print( char*79 )
  105.  
  106.  
  107. #==============================================================================
  108. # Parameters
  109. INPUT = "labelsRaw_Test.txt"
  110. #INPUT = r"D:\PPPV\Cut\MLP\0102\0102Raw.txt"
  111.  
  112. # Shall the program save the file or just checks for goofs?
  113. SAVE_FILE = True
  114. OUTPUT = "labels.txt"
  115.  
  116. # Shall the program autoreplace typos?
  117. REPLACE_TYPO = True
  118.  
  119. # Shall the program autoreplace leftover abbreviations?
  120. REPLACE_LEFTOVER = True
  121.  
  122. # Shall the program autoreplace ending punctuation?
  123. REPLACE_ENDING_PUNCTUATION = True
  124.  
  125. # Shall the program autoreplace transcript abbreviations?
  126. REPLACE_ABBREVIATIONS = True
  127.  
  128. # Error level to display or not stuff.
  129. # 0 : errors only
  130. # 1 : errors and warning
  131. # 2 : errors, warning and good
  132. # 3 : errors, warning, good and infos
  133. ERROR_LEVEL = 3
  134.  
  135.  
  136. # Shall not modify after this line
  137. #=============================================================================
  138. draw_spacer()
  139. print( "Welcome to label checker V "+str(VERSION) )
  140. print( "Let me bitch about your typo and other mistakes..." )
  141. print()
  142. print( "input\t: " + INPUT )
  143. print( "output\t: " + OUTPUT )
  144. bools = ["Nope", "Eyup"]
  145. print( "Replace typos    \t: " + bools[int(REPLACE_TYPO)] )
  146. print( "Replace leftovers\t: " + bools[int(REPLACE_LEFTOVER)] )
  147. print( "Replace punctuation\t: " + bools[int(REPLACE_ENDING_PUNCTUATION)] )
  148. print( "Replace abbreviations\t: " + bools[int(REPLACE_ABBREVIATIONS)] )
  149.  
  150. if (int(REPLACE_TYPO) + int(REPLACE_LEFTOVER) + int(REPLACE_ENDING_PUNCTUATION) + int(REPLACE_ABBREVIATIONS) ) > 3 :
  151.     print( "(You shouldn't put that much trust in me...)" )
  152.  
  153. whine = ["warning only", "warning and error", "boringly verbose", "worst than your ex"]
  154. print( "Whining level\t: " + whine[ERROR_LEVEL] )
  155. draw_spacer()
  156. print()
  157.  
  158. abbreviations = {
  159.     "names" : {
  160.         "Twilight":["twilight sparkle", "ts", "twi"],
  161.         "Pinkie":["pinkie pie", "pp"],
  162.         "Applejack":["aj", "apl"],
  163.         "Rainbow":["rainbow dash", "rd"],
  164.         "Rarity":["ra", "rar"],
  165.         "Fluttershy":["fs", "flu"],
  166.         "Spike":["sp", "spi"],
  167.         "Celestia":["princess celestia", "ce", "cel", "celly"],
  168.         "Luna":["princess luna", "lu"],
  169.         "Apple Bloom":["ab"],
  170.         "Sweetie Belle":["sb"],
  171.         "Scootaloo":["sc", "chicken"],
  172.         "Diamond Tiarra":["dt"],
  173.         "Silver Spoon":["ss"],
  174.         "Cheerlee":["ch"],
  175.         "Iron Will":["i"],
  176.         "Cadence":["princess cadence", "cad"],
  177.         "Shining Armor":["sa"],
  178.         "Chrysalis":["queen chrysalis", "cr", "bug butt"],
  179.         "Nightmare Moon":["nm"],
  180.         "Grany Smith":["gs"],
  181.         "Mayor Mare":["mm"],
  182.         "Babs Seed":["bs"],
  183.         "Spitfire":["sf"],
  184.         "Lightning Dust":["ld"]
  185.     },
  186.     "moods" : {
  187.         "Neutral":["n"],
  188.         "Happy":["h"],
  189.         "Amused":["am"],
  190.         "Sad":["s"],
  191.         "Annoyed":["a"],
  192.         "Angry":["ag"],
  193.         "Disgust":["d"],
  194.         "Sarcastic":["sa"],
  195.         "Smug":["sm"],
  196.         "Fear":["f"],
  197.         "Anxious":["ax"],
  198.         "Confused":["c"],
  199.         "Surprised":["su"],
  200.         "Tired":["t"],
  201.         "Whispering":["w"],
  202.         "Shouting":["sh"],
  203.         "Whining":["wh"]
  204.     },
  205.     "noise" : {
  206.         "Noisy":["q", "n"],
  207.         "Very Noisy":["qq", "vn"]
  208.     },
  209.     "transcript" : {
  210.         "mister" : "mr",
  211.         "miss" : "ms"
  212.     }
  213. }
  214.  
  215.  
  216. characters = []
  217.  
  218. # Reads the labels file
  219. try :
  220.     file = open( INPUT, "r" )
  221.     labelData = file.readlines()
  222.    
  223. except NameError as e :
  224.     error( "File " + INPUT + " can't be found." )
  225.    
  226. except IOError as e :
  227.     error( "IO error {0} when trying to access the file : {1}".format( e.errno, e.strerror ) )
  228.    
  229. finally :
  230.     file.close()
  231.    
  232.  
  233. # Gather informations from label file
  234.  
  235. episode = {}
  236. lines = []
  237.  
  238. #-----------------------------------------------------------------------------
  239. # Work on each label
  240.  
  241. for index in range( len(labelData) ) :
  242.     # By default, the line shall be defective to be absolutely sure. But I'm lazy
  243.     rottenLine = False
  244.    
  245.     line = labelData[index]
  246.    
  247.     if line.rstrip() == "" :
  248.         warning( "Empty line " + str(index +1 ) )
  249.         rottenLine = True
  250.     else :
  251.        
  252.         if line.count("\t") != 2 :
  253.             error( "Malformed line " + str(index +1 ) + " : Check tabulations on label" )
  254.             rottenLine = True
  255.         else :
  256.             start, end, label = line.split( "\t" )
  257.            
  258.             start = start
  259.             end = end
  260.             label = label.rstrip()
  261.            
  262.             length = float(end) - float(start)
  263.             hour, minute, second, milli, trash = timestampToTime( float(start) )
  264.            
  265.             entry = "{hour:0>2}{minute:0>2}{second:0>2}".format( hour=hour, minute=minute, second=second)
  266.            
  267.             #-----------------------------------------------------------------
  268.             # Checks the label content
  269.             underscoreNumber = label.count("_")
  270.            
  271.             if underscoreNumber == 6 :
  272.                 info( "Line " + str(index +1) + " : Timestamp already here" )
  273.                 h, m, s, character, moods, noise, transcript = label.split( "_" )
  274.                
  275.             elif underscoreNumber == 3 :
  276.                 character, moods, noise, transcript = label.split( "_" )
  277.                
  278.             else :
  279.                 error( "Malformed line " +str(index +1 ) + " : Check underscores" )
  280.                 rottenLine = True
  281.                
  282.             if not rottenLine :
  283.                 #-------------------------------------------------------------
  284.                 # Character checks
  285.                 if character != "" :
  286.                     # Typo checks
  287.                     for char in abbreviations["names"] :
  288.                         if character != char :
  289.                             if likeness( character, char ) > 0.85 :
  290.                                 if REPLACE_TYPO :
  291.                                     info( "Line " + str(index +1 ) + " name : " + character + " replaced by " + char )
  292.                                     character = char
  293.                                 else :
  294.                                     warning( "Line " + str(index +1 ) + " name : " + character + " used. Do you mean " + char + "?" )
  295.                    
  296.                     # Abbreviations checks
  297.                     for char in abbreviations["names"] :
  298.                         if character.lower() in abbreviations["names"][char] :
  299.                             if REPLACE_LEFTOVER :
  300.                                 info( "Line " + str(index +1 ) + " name : " + character + " replaced by " + char )
  301.                                 character = char
  302.                             else :
  303.                                 warning( "Line " + str(index +1 ) + " name : " + character + " used. Do you mean " + char + "?" )
  304.                 else :
  305.                     error( "Line " + str(index +1 ) + " : No character" )
  306.                     rottenLine = True
  307.                
  308.                 #-------------------------------------------------------------
  309.                 # Mood checks
  310.                 if moods != "" :
  311.                     m = moods.split()
  312.                    
  313.                     # For each mood in the label
  314.                     for id in range( len(m) ) :
  315.                        
  316.                         # Typo checks
  317.                         for mood in abbreviations["moods"] :
  318.                             if m[id] != mood :
  319.                                 if likeness( m[id], mood ) > 0.85 :
  320.                                     if REPLACE_TYPO :
  321.                                         info( "Line " + str(index +1 ) + " mood : " + m[id] + " replaced by " + mood )
  322.                                         m[id] = mood
  323.                                     else :
  324.                                         warning( "Line " + str(index +1 ) + " mood : " + m[id] + " used. Do you mean " + mood + "?" )
  325.                        
  326.                         # Abbreviations checks
  327.                         # Checks against each known mood leftover abbreviation
  328.                         for mood in abbreviations["moods"] :
  329.                             if m[id].lower() in abbreviations["moods"][mood] :
  330.                                 if REPLACE_LEFTOVER :
  331.                                     info( "Line " + str(index +1 ) + " mood : " + m[id] + " replaced by " + mood )
  332.                                     m[id] = mood
  333.                                 else :
  334.                                     warning( "Line " + str(index +1 ) + " mood : " + m[id] + " used. Do you mean " + mood + "?" )
  335.                        
  336.                         # Checks if the mod is known
  337.                         m[id] = m[id].capitalize()
  338.                         if m[id] not in abbreviations["moods"] :
  339.                             warning( "Line "+str(index +1)+" mood : '" + m[id] + "' unknown. Can't check it" )
  340.                    
  341.                     # Construct back the string. Obviously a more pythonic way exists, but I'm a lazy fuck.
  342.                     moods = ""
  343.                     for id in range( len(m) ) :
  344.                         if id > 0 :
  345.                             moods += " "
  346.                         moods += m[id]
  347.                    
  348.                 else :
  349.                     error( "Line " + str(index +1 ) + " : No mood" )
  350.                     rottenLine = True
  351.                
  352.                 #-------------------------------------------------------------
  353.                 # Noise checks
  354.                 if noise != "" :
  355.                     for n in abbreviations["noise"] :
  356.                        
  357.                         # Abbreviation check
  358.                         if noise in abbreviations["noise"][n] :
  359.                             if REPLACE_LEFTOVER :
  360.                                 info( "Line " + str(index +1 ) + " noise : " + noise + " replaced by " + n )
  361.                                 noise = n
  362.                             else :
  363.                                 warning( "Line " + str(index +1 ) + " noise : " + noise + " used. Do you mean " + n + "?" )
  364.                        
  365.                         # Typo check
  366.                         if noise != n :
  367.                             if likeness( noise.lower(), n.lower() ) > 0.85 :
  368.                                 if REPLACE_TYPO :
  369.                                     info( "Line " + str(index +1) + " noise : " + noise + " replaced by " + n )
  370.                                     noise = n
  371.                                 else :
  372.                                     warning( "Line " + str(index +1) + " noise : " + noise + "used. Do you mean " + n + "?" )
  373.                        
  374.                    
  375.                     if noise.lower() not in ["", "noisy", "very noisy"] :
  376.                         error( "Line " + str(index +1) + " noise is " + noise + " ; shall be nothing, 'noisy' or 'very noisy'" )
  377.                         rottenLine = True
  378.                
  379.                 #-------------------------------------------------------------
  380.                 # Transcript checks
  381.                 if transcript != "" :
  382.                    
  383.                     # Check for ending punctuation
  384.                     if transcript[-1] not in ",.!?" :
  385.                         ending = ""
  386.                         m = moods.split()
  387.                         for mood in m :
  388.                             if mood in ["Happy", "Angry", "Fear", "Anxious", "Surprised", "Shouting"] :
  389.                                 if ending.count("!") == 0 :
  390.                                     ending += "!"
  391.                             elif mood in ["Annoyed", "Sarcastic", "Confused"] :
  392.                                 if ending.count("?") == 0 :
  393.                                     ending += "?"
  394.                        
  395.                         if ending == "" :
  396.                             ending = "."
  397.                        
  398.                         if REPLACE_ENDING_PUNCTUATION :
  399.                             info( "Line " + str(index +1) + " trans : No punctuation. Guestimate based on mood : " + ending + " (please, do check, I'm not good with emotions...)" )
  400.                             transcript += ending
  401.                         else :
  402.                             warning( "Line " + str(index +1) + " trans : No punctuation. (Guestimate based on mood : "+ending+" )" )
  403.                    
  404.                     # Check for numbers and abbreviations
  405.                     words = transcript.split( " " )
  406.                     trans = ""
  407.                     for word in words :
  408.                        
  409.                         # Numbers
  410.                         if word.isdigit() :
  411.                             if REPLACE_ABBREVIATIONS :
  412.                                 number = num2str( int(word) )
  413.                                 info( "Line "+str(index +1)+" : "+ word+" expanded to " + number )
  414.                                 word = number # Yay, that's duck typing! (kidding, both are string, but you got the joke, right? Ri-right?)
  415.                        
  416.                         for abb in abbreviations["transcript"] :
  417.                             #if abbreviations["transcript"][abb] in word :
  418.                             if abbreviations["transcript"][abb] == word :
  419.                                 info( "Line "+str(index +1)+" : " + word+" expanded to " + abb)
  420.                                 word = abb
  421.                        
  422.                         # Rebuild the transcript
  423.                         if trans != "" :
  424.                             trans += " "
  425.                         trans += word
  426.                    
  427.                     transcript = trans
  428.                    
  429.                 else :
  430.                     error( "Line " + str(index +1 ) + " : No transcript" )
  431.                     rottenLine = True
  432.                
  433.     #-------------------------------------------------------------------------
  434.     # If no errors, keep the line
  435.     if not rottenLine :
  436.         lines.append( f"{start}\t{end}\t{hour:0>2}_{minute:0>2}_{second:0>2}_{character}_{moods}_{noise}_{transcript}" )
  437.     else :
  438.         info( "Line " + str(index +1 ) + " dropped." )
  439.    
  440.  
  441.  
  442. # Save to file if asked
  443. if SAVE_FILE :
  444.     try :
  445.         file = open( OUTPUT, "w" )
  446.         for line in lines :
  447.             file.write( line + "\n" )
  448.         info( "File saved" )
  449.        
  450.     except NameError as e :
  451.         error( "File " + OUTPUT + " can't be found." )
  452.        
  453.     except IOError as e :
  454.         error( "IO error {0} when trying to access the file : {1}".format( e.errno, e.strerror ) )
  455.        
  456.     finally :
  457.         file.close()
  458. else :
  459.     for line in lines :
  460.         print( line )
  461.     info( "Nothing saved to the disk." )
  462.  
  463. input("Press enter to quit.")
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!