This project aims to provide an intelligent visual aid for blind and visually impaired to help them navigate their environment, read newpapers, books and magazines and also browse the internet iGlass v2.0 workflow

Linux: All the installations where run and tested on a linux OS of both the system and raspberry pi. It will likely work on a Windows OS. Open-source Libraries Used:

• Chatterbot: an offline chatbot system
• beautifulsoup: python webscraping engine
• pyttsx3: python based offline speech-to-text
• SpeechRecognition: speech recongition library with apis from google, ibm, pocketsphinx
• pico2wave: text-to-speech based on android system (this is smoother than pyttsx3 which is based on espeak)
• picamera: Python interface to the Raspberry Pi camera modules
• google-cloud-vision
• espeak: speech synthesizer

sudo apt-get update
sudo apt-get updgrade
sudo apt-get python3-pip3
sudo apt-get python-pip

pip3 install picamera

This library is not used anymore. Google DialogFlow works more efficiently for chatterbot

pip3 install Chatterbot==1.0.2

Documentation: https://chatterbot.readthedocs.io/en/stable/

sudo pip install dialogflow

Documentation: https://cloud.google.com/dialogflow/es/docs
Python Reference: https://cloud.google.com/dialogflow/es/docs/reference/libraries/python

sudo pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib

sudo pip3 install --upgrade oauth2client google-auth

pip3 install google-cloud-vision

pip3 install beautifulsoup4

Documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/

pip3 install pyttsx3==2.7

Documentation: https://pyttsx3.readthedocs.io/en/latest/

pip3 install SpeechRecognition

Documentation: https://pypi.org/project/SpeechRecognition/
Reference: https://realpython.com/python-speech-recognition/

sudo apt-get install python-pyaudio python3-pyaudio

or

sudo pip install pyaudio

sudo apt-get install espeak

cd /
sudo wget http://incrediblepbx.com/picotts-raspi.tar.gz
tar zxvf picotts-raspi.tar.gz
sudo rm -f picotts-raspi.tar.gz
sudo -i
cd /root
echo "Installing Pico TTS..."
./picotts-install.sh
exit

Note: if the file does not exist, download file from my google drive shareable link: https://drive.google.com/open?id=1sS_KsSReNerkX0pRMtqTlFPPwjLm8-mZ and use filezilla, WinSCP(Windows Machine) or scp command to move the picotts-raspi.tar.gz to the root directory of your pi.

sudo apt-get install asterisk
cd /etc/asterisk
cp extensions.conf extensions_customs.conf
chown asterisk:asterisk extensions_custom.conf  # changes ownership user_group=asterisk and user=asterisk

• set up a new cloud progect google project
• create credentials and set role to admin
• create and download key of created credential in json format. checkout this guide copy the download folder to a specified folder of raspberry pi (in this case it was stored in a '.keys/' folder)

sudo nano /etc/profile

copy the next line of command into the last line of /etc/profile file

export GOOGLE_APPLICATION_CREDENTIALS="[PATH]"

verify if the environment variable has been added successfully

printenv

Here is a guide on getting started with authentication

• disabled/black default audio card

  > echo 'blacklist snd_bcm2835' > /etc/modprobe.d/raspi-blacklist.conf
  

• Open /lib/modprobe.d/aliases.conf and comment out the line options snd-usb-audio index=-2

• modify the alsamixer settings before saving

  > alsamixer
  

• store the modifications to a file

  > alsactl --file asound.state store
  

• command to load alsa state

  > alsactl --file asound.state restore
  

ALSA lib confmisc.c:768:(parse_card) cannot find card '0'
ALSA lib conf.c:4292:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
ALSA lib conf.c:4292:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1251:(snd_func_refer) error evaluating name
...

This is likely occurs from incorrect configuration when setting up ALSA

• confirm the proper card number, device number and subdevice number using the command:

  > aplay -l
  

  **** List of CAPTURE Hardware Devices ****
  card 0: seeed2micvoicec [seeed-2mic-voicecard], device 0: bcm2835-i2s-wm8960-hifi wm8960-hifi-0 []
    Subdevices: 1/1
    Subdevice #0: subdevice #0
  
  

• edit the file ~/.asoundrc with proper device numbers

  > sudo nano ~/.asoundrc
  

  into:

  pcm.!default {
    type plug
    slave {
      pcm "hw:0,0"
    }
  }
  
  ctl.!default {
      type hw
      card 0
  }
  

• also, edit the file /usr/share/alsa/alsa.conf

  sudo nano /usr/share/alsa/alsa.conf
  

  search and replace the following lines with proper numbers

  ...
  defaults.ctl.card 0
  defaults.pcm.card 0
  ...
  

upon trying to import the dialogflow library it might display an INVALID ARGUMENT error This github discussion helped alot I tried building grpcio<\i> library from source but it keeps failing (my raspberry pi disconnects entirely from wi-fi) I had to install a pervious version of grpcio<\i> for it to work. Here the are fixes:

sudo pip uninstall grpc grpcio
rm -rf ~/.cache/pip/*
sudo pip3 install grpcio==1.29.0