Upload a video on how to setup the program, start from downloading…

Question Answered step-by-step Upload a video on how to setup the program, start from downloading… Upload a video on how to setup the program, start from downloading and installing the needed softwares. Then cmd, then the other methods required to run the program. This is going to be tricky, but follow my instructions carefully and this should work.First you need to install:pyaudio and SpeechRecognition modules on your windows computer(assuming you have pip and python installed already):Just open the Command Prompt or CMD(click on windows button and type cmd )These are the commands that you need to run in order to install these modules:pip install pyaudio pip install SpeechRecognitionOnce you have these installed, the rest of the steps are easy to follow.First you need to import the speech_recognition module:import speech_recognition as srand then the winsound module that is going to generate the beep:import winsoundSet the frequency to 2500 (2500 hertz) and duration to 1000 (1000 ms = 1 second)frequency = 2500  # Set Frequency To 2500 Hertzduration = 1000  # Set Duration To 1000 ms == 1 secondCreate the empty database for the detected words_wordsDetected=[]create the recognizer object:r = sr.Recognizer()Now this is what we use to listen from a microphone and store the binary data in a variable called audio:with sr.Microphone() as source:   audio = r.listen(source)Now we can use the google speech to text function that comes with the speech_recognizer library to convert the audio(which is stored in binary) to text:result = r.recognize_google(audio)Now we use the similar for loop as before but this time we include the part where when we find a bad word, we save that audio in a audio file(binary to wav format):for x in profinity:   if x in result:    with open(‘speech.wav’,’wb’) as f:        f.write(audio.get_wav_data())     print(‘Bad Word Detected is : ‘,x)    now = datetime.now()    winsound.Beep(frequency, duration)    wordsDetected.append(x)    wordsDetected.append(str(now))The database works the same but this time we will have records. Whole Code:import speech_recognition as srimport winsoundfrom datetime import datetime  frequency = 2500  # Set Frequency To 2500 Hertzduration = 1000  # Set Duration To 1000 ms == 1 second  wordsDetected=[]r = sr.Recognizer() profinity=[“ukinnam”,”salsal”,”gungong”,”test”,”weirdo”] with sr.Microphone() as source:   audio = r.listen(source)      result = r.recognize_google(audio) for x in profinity:   if x in result:    with open(‘speech.wav’,’wb’) as f:        f.write(audio.get_wav_data())     print(‘Bad Word Detected is : ‘,x)    now = datetime.now()    winsound.Beep(frequency, duration)    wordsDetected.append(x)    wordsDetected.append(str(now))    print(“All detected Bad words and Time:”)print(wordsDetected)Output:Image transcription textLa Python 3.7.9 Shell 0 X File Edit Shell Debug Options Window Help Python 3.7.9 (tags/v3.7.9:13094747c7,Aug 17 2020, 16:30:00) [MSC v. 1900 64 bit (AMD64) ] on win32 Type “help”,”copyright”, “credits” or “license ()” for more information. > &… Show more… Show more UPLOAD THE VIDEO IN THE GOOGLE DRIVE.  Computer Science Engineering & Technology Python Programming Share QuestionEmailCopy link Comments (0)