create app.py

app.py

@@ -0,0 +1,150 @@
+# Installing Necessary Packages
+
+!pip install transformers
+!pip install torch
+!pip install opencv-python
+!pip install openai
+!pip install sentencepiece
+
+# Importing Necessary Packages and classes
+
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+from IPython.display import display, Javascript
+from google.colab.output import eval_js
+from base64 import b64decode
+from IPython.display import Image
+import cv2
+import openai
+import os
+import pandas as pd
+import time
+from transformers import BarkModel, BarkProcessor
+from IPython.display import Audio
+
+# Defining the camera in the system
+
+def take_photo(filename='photo.jpg', quality=0.8):
+  js = Javascript('''
+    async function takePhoto(quality) {
+      const div = document.createElement('div');
+      const capture = document.createElement('button');
+      capture.textContent = 'Capture';
+      div.appendChild(capture);
+
+      const video = document.createElement('video');
+      video.style.display = 'block';
+      const stream = await navigator.mediaDevices.getUserMedia({video: true});
+
+      document.body.appendChild(div);
+      div.appendChild(video);
+      video.srcObject = stream;
+      await video.play();
+
+      // Resize the output to fit the video element.
+      google.colab.output.setIframeHeight(document.documentElement.scrollHeight, true);
+
+      // Wait for Capture to be clicked.
+      await new Promise((resolve) => capture.onclick = resolve);
+
+      const canvas = document.createElement('canvas');
+      canvas.width = video.videoWidth;
+      canvas.height = video.videoHeight;
+      canvas.getContext('2d').drawImage(video, 0, 0);
+      stream.getVideoTracks()[0].stop();
+      div.remove();
+      return canvas.toDataURL('image/jpeg', quality);
+    }
+    ''')
+  display(js)
+  data = eval_js('takePhoto({})'.format(quality))
+  binary = b64decode(data.split(',')[1])
+  with open(filename, 'wb') as f:
+    f.write(binary)
+  return filename
+
+# Capturing snaps using given button and saving them
+
+try:
+  filename = take_photo()
+  print('Saved to {}'.format(filename))
+
+  # Show the image which was just taken.
+  display(Image(filename))
+except Exception as err:
+  # Errors will be thrown if the user does not have a webcam or if they do not
+  # grant the page permission to access it.
+  print(str(err))
+
+# 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)
+
+# Importing a English Text-To-Speech Model from huggingface
+
+tts_model = BarkModel.from_pretrained("suno/bark-small")
+tts_processor = BarkProcessor.from_pretrained("suno/bark-small")
+
+# Preprocessing the text data using imported preprocessor and generating output from model
+
+inputs = tts_processor(response, voice_preset="v2/en_speaker_3")
+
+speech_output = tts_model.generate(**inputs).cpu().numpy()
+
+# Output of generated speech
+
+sampling_rate = tts_model.generation_config.sample_rate
+Audio(speech_output[0], rate=sampling_rate)