Merge pull request #657 from avats101/main

Added Image to Speech

image_to_speech/README.md

@@ -0,0 +1,27 @@
+USER GUIDE
+Setup and activate virtual environment :
+
+For Unix based systems please execute the following command to create venv and install requirements.
+
+make init
+source .venv/bin/activate
+
+Pre-requisites
+
+1) Python pillow (PIL)
+$ pip install pillow
+
+2) Python pytesseract (py package wrapper)
+$ pip install pytesseract
+
+3) Tesseract (OCR Tool)
+Download from here https://github.com/tesseract-ocr/tesseract/releases
+
+4) Python pyttsx3 (Text-to-Speech)
+$ pip install pyttsx3
+
+How to run the script?
+
+    $ python image_to_speech.py
+
+Once done, Speech would be produced for the given text image

image_to_speech/image_to_speech.py

@@ -0,0 +1,12 @@
+import pytesseract
+from PIL import Image
+import pyttsx3
+img = Image.open('Location_to_Image/text_image.png')
+pytesseract.pytesseract.tesseract_cmd = 'C:/Program Files/Tesseract-OCR/tesseract.exe'
+result = pytesseract.image_to_string(img)
+with open('text.txt', mode='w') as file:
+    file.write(result)
+    print(result)
+engine = pyttsx3.init()
+engine.say(result)
+engine.runAndWait()

image_to_speech/requirements.txt

@@ -0,0 +1,3 @@
+pytesseract
+pillow
+pyttsx3