Commit 794a4c4

authored

Merge pull request avinashkranjan#786 from Amit366/Amit

Image to speech

2 parents 5a4b79f + 321e32d commit 794a4c4Copy full SHA for 794a4c4

File tree

+68

-0

lines changed

+68

-0

lines changed

Lines changed: 38 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,38 @@`
	`1`	`+# <b>Image To Speech File</b>`
	`2`	`+`
	`3`	`+[![forthebadge](https://forthebadge.com/images/badges/made-with-python.svg)](https://forthebadge.com)`
	`4`	`+`
	`5`	`+## Image To Speech Functionalities : 🚀`
	`6`	`+`
	`7`	`+- The script converts an image to text and speech files`
	`8`	`+- At the end the script asks whether to save or delete files`
	`9`	`+`
	`10`	`+## Image To Speech Instructions: 👨🏻‍💻`
	`11`	`+`
	`12`	`+### Step 1:`
	`13`	`+`
	`14`	`+ Open Termnial 💻`
	`15`	`+`
	`16`	`+### Step 2:`
	`17`	`+`
	`18`	`+ Locate to the directory where python file is located 📂`
	`19`	`+`
	`20`	`+### Step 3:`
	`21`	`+`
	`22`	`+ Run the command: python image_to_speech.py/python3 image_to_speech.py 🧐`
	`23`	`+`
	`24`	`+### Step 4:`
	`25`	`+`
	`26`	`+ Sit back and Relax. Let the Script do the Job. ☕`
	`27`	`+`
	`28`	`+### Requirements`
	`29`	`+`
	`30`	`+ - pytesseract`
	`31`	`+ - PIL`
	`32`	`+ - gTTS`
	`33`	`+ - os`
	`34`	`+`
	`35`	`+## Author`
	`36`	`+`
	`37`	`+ Amit Kumar Mishra`
	`38`	`+`

Lines changed: 30 additions & 0 deletions

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,30 @@`
	`1`	`+import pytesseract`
	`2`	`+from PIL import Image`
	`3`	`+from gtts import gTTS`
	`4`	`+import os`
	`5`	`+`
	`6`	`+`
	`7`	`+pytesseract.pytesseract.tesseract_cmd = input(r'Enter the path for pytesseract: ')`
	`8`	`+`
	`9`	`+img = input(r"Enter the path for image: ")`
	`10`	`+target = Image.open(img)`
	`11`	`+text = pytesseract.image_to_string(target, config='')`
	`12`	`+`
	`13`	`+with open(f"./Imagetospeech/text.txt",'w') as f:`
	`14`	`+ f.write(text)`
	`15`	`+`
	`16`	`+file = open(r'./Imagetospeech/text.txt')`
	`17`	`+mytext = file.read().replace("\n"," ")`
	`18`	`+language = 'en'`
	`19`	`+output = gTTS(text=mytext, lang=language, slow=False)`
	`20`	`+output.save('./Imagetospeech/imagetospeech.mp3')`
	`21`	`+file.close()`
	`22`	`+os.system("start ./Imagetospeech/imagetospeech.mp3")`
	`23`	`+`
	`24`	`+question = input("Do you want to delete the files (Y/N): ")`
	`25`	`+if question=='Y'or question=='y':`
	`26`	`+ os.remove('./Imagetospeech/text.txt')`
	`27`	`+ os.remove('./Imagetospeech/imagetospeech.mp3')`
	`28`	`+`
	`29`	`+elif question=='N'or question=='n':`
	`30`	`+ print("Files saved")`

Comments

(0)