app.py

# Importing Necessary Packages and classes

from transformers import AutoImageProcessor, AutoModelForImageClassification
from IPython.display import display, Javascript
from base64 import b64decode
from IPython.display import Image
import cv2
import openai
import pandas as pd
import time
from transformers import BarkModel, BarkProcessor
from IPython.display import Audio
import playsound

'''

# Using captured images

import cv2

# Open a connection to the webcam (0 is usually the default webcam)
cap = cv2.VideoCapture(0)

# Check if the webcam is opened successfully
if not cap.isOpened():
    print("Error: Could not open the webcam.")
    exit()

while True:
    # Read a frame from the webcam
    ret, frame = cap.read()

    # Display the captured frame
    cv2.imshow('Webcam', frame)

    break

# Release the webcam and close the OpenCV windows
cap.release()
cv2.destroyAllWindows()

image=frame

'''

image = cv2.imread('n02106662_320.jpg')


# Using the pre-trained Dog Breed Identification Model

image_processor = AutoImageProcessor.from_pretrained("wesleyacheng/dog-breeds-multiclass-image-classification-with-vit")
dog_breed_model = AutoModelForImageClassification.from_pretrained("wesleyacheng/dog-breeds-multiclass-image-classification-with-vit")

# Importing the saved image

#img_path='/content/n02088094_60.jpg'

#image=cv2.imread(img_path)

# Preprocessing the captured image using pre-trained model based preprocessor

inputs = image_processor(images=image, return_tensors="pt")

# Predicting the output using model from huggingface

outputs = dog_breed_model(**inputs)
logits = outputs.logits

# Finding the exact output class and corresponding label

predicted_class_idx = logits.argmax(-1).item()

predicted_class_actual=dog_breed_model.config.id2label[predicted_class_idx]
predicted_class_actual=predicted_class_actual.split("_")

str1=""

for ele in predicted_class_actual:
  str1+=ele+" "

print("Predicted class:", str1)

# Specifying the OpenAI API key

openai.api_key = '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'

# Specifying the chatGPT engine

def get_completion(prompt, model="gpt-3.5-turbo"):

  messages = [{"role": "user", "content": prompt}]
  response = openai.ChatCompletion.create(
  model=model,
  messages=messages,
  temperature=0,
  )
  return response.choices[0].message["content"]

# Getting simple data from ChatGPT API

prompt = "chracterstics and behaviour of "+str1+" in a paragraph"

response = get_completion(prompt)

print(response)

# Import the Gtts module for text  
# to speech conversion 
from gtts import gTTS 
  
# import Os module to start the audio file
import os 

# Language we want to use 
language = 'en'

output = gTTS(text=response, lang=language, slow=False)

output.save("output.mp3")

Audio("output.mp3",rate=24000)