This project was created by

• Subhadeep Mandal
• Aditya Charan P N
• Dharniesh P R

Step 1: Install pytorch on your windows system with this command

• pip3 install torch==1.10.0+cu113 torchvision==0.11.1+cu113 torchaudio===0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html

Step 2: Install nltk with this command

• pip install nltk

Step 3: Install numpy with this command

• pip install numpy

Step 4: Install SpeechRecognition with this command

• pip install SpeechRecognition

Step 5: Install pyttsx3 with this command

• pip install pyttsx3

Step 6: Install pywhatkit with this command

• pip install pywhatkit

Step 7: Install wikipedia with this command

• pip install wikipedia

Step 8: Download this file for pyaudio from https://download.lfd.uci.edu/pythonlibs/w6tyco5e/PyAudio-0.2.11-cp39-cp39-win_amd64.whl go to its directory and install it with this command

• pip install PyAudio-0.2.11-cp39-cp39-win_amd64.whl

Step 9: Run nltk_utils.py after removing the # on line 3 to download punkt

Step 10: Run train.py which will generate the data.pth file

Step 11: Run app.py