UnicodeDecodeError: 'utf8' codec can't decode byte 0x80 - invalid start byte

dirName = sys.argv[1]
files = [ f for f in listdir(dirName) if isfile(join(dirName,f)) ]
 
for fileName in files:
    f = codecs.open(dirName + "/" + fileName , 'r' , "utf-8")
    text = f.read()
    prevPosition = 0
    position = 0
    while True:
        tmp = countStringLengthByNumberOfWordsFromPosition(text, 1000, prevPosition)
        if tmp != None:
            position += tmp
            TextAtoms.append(CountStatsForString(text[prevPosition : position], str(fileName)[:-4]))
        if abs(len(text) - prevPosition) < 1000:
            break
        else:
            prevPosition = position
    
    f.close()

import wave
wav=wave.open("sound.wav",mode='r')
(nchannels, sampwidth, framerate, nframes, comptype, compname) = wav.getparams()
content = wav.readframes(nframes)
f=open('qwerty.txt','w')
f.write(content.decode('utf-8'))
f.close()

def CountStatsForString(string, author):
    totalCount = 0
    totalWordLength = 0.0
    words = set()
 
    POSes = {'NOUN' : 0.0, 'ADJF' : 0.0, 'ADJS' : 0.0, 'COMP' : 0.0, 'VERB' : 0.0, 'INFN' : 0.0, 'PRTF' : 0.0, 'PRTS' : 0.0, 'GRND' : 0.0, 'NUMR' : 0.0, 'ADVB' : 0.0, 'NPRO' : 0.0, 'PRED' : 0.0, 'PREP' : 0.0, 'CONJ' : 0.0, 'PRCL' : 0.0, 'INTJ' : 0.0,}
 
    if author not in AuthorsVocabulary.keys():
        AuthorsVocabulary[author] = set()
    totalSentenceNumber = float(len(re.findall(r"[.!?]+", string)))
    wordList = re.split('[., ;?:!\n\'\"]+', string)
    for word in wordList:
        if ((morph.parse(word.lower())[0]).tag.POS != None):
            POSes[(morph.parse(word)[0]).tag.POS] += 1.0
            totalCount += 1
            totalWordLength += float(len(word))
            words.add(word.lower())
            AuthorsVocabulary[author].add(word.lower())
 
    if totalCount != 0:
        for key in POSes.keys():
            POSes[key] /= (float(totalCount)/100.0)
        
        txtAtom = TextAtom(author, POSes, totalWordLength/float(totalCount), float(totalCount)/totalSentenceNumber, len(wordList))
        return txtAtom
    else:
        return None
 
def countStringLengthByNumberOfWordsFromPosition (string, numberOfWords, initPosition):
    if initPosition < len(string):
        str = string[initPosition:]
        totalLength = numberOfWords - 1
        wordList = re.split('[ ]+', str)
        j = min (numberOfWords, len(wordList))
        for i in xrange(0, min(numberOfWords, len(wordList))):
            totalLength += len(wordList[i])
        #if str[totalLength - 1] != ('.' or '!' or '?'):
        #   while j < len(wordList) - 1 and str[totalLength - 1] != ('.' or '!' or '?'):
        #       totalLength += (1 + len(wordList[j + 1]))
        #       j += 1
        return totalLength
    else:
        return None

import wave
 
wav = wave.open('30 Seconds To Mars - Attack.wav', mode='r')
nchannels, sampwidth, framerate, nframes, comptype, compname = wav.getparams()
 
content = wav.readframes(nframes)
 
out = wave.open('qwerty.wav', 'w')
out.setparams((nchannels, sampwidth, framerate, framerate * 183, 'NONE', 'Uncompressed'))
out.writeframes(content)
out.close()