Update app.py

app.py

@@ -1,41 +1,50 @@
+# -*- coding: utf-8 -*-
+"""Class.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1uVVBU3JO2eo-Ms0r5J_wAjtGByiGXSR9
+"""
+
 import streamlit as st
 from transformers import pipeline
 from PIL import Image
 
-# Creates a brief description of a picture using a smart model
+# Creates a brief description for the pictures
 def generate_caption(image):
-    with st.spinner("🔍 Looking at your picture..."):
+    with st.spinner("Analysing the Pictures for Key Message..."):
         # Loads the BLIP model to examine and describe the picture
-        image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+        image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
         caption = image_to_text(image)[0]["generated_text"]
     return caption
 
 # Builds a story from the picture’s description
 def generate_story(caption):
-    with st.spinner("✍️ Writing a fun story..."):
-        # Uses a story model to craft a tale from the description
-        pipe = pipeline("text-generation", model="pranavpsv/genre-story-generator-v2")
+    with st.spinner("Enhancing the Story for better Details..."):
+        # Uses the text generation model to create a story based on the description
+        pipe = pipeline("text-generation", model="TheBloke/phi-2-GGUF")
         story = pipe(caption)[0]['generated_text']
     return story
 
-# Turns the story into spoken audio
+# Turns the story into audio
 def generate_audio(story):
-    with st.spinner("🎙️ Turning story into audio..."):
-        # Uses a speech model to read the story aloud
-        pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+    with st.spinner("Turning story into News audio..."):
+        # Uses a speech model to turn description into audio
+        pipe = pipeline("text-to-speech", model="hexgrad/Kokoro-82M")
         audio = pipe(story)
     return audio
 
-# Streamlit UI: Makes a simple interface for kids to enjoy stories
+# Streamlit UI: Makes a simple interface to generate the audio
 
-# Displays a fun title
-st.title("Picture to Story Fun! 🌈")
+# Displays the title
+st.title("Tool for the Reporter - Turning the News Photo into Audio")
 
-# Describes the app for young users
-st.write("Hi, kids! Share a picture to get a fun story! Great for ages 3-10.")
+# Describes the app for users
+st.write("Please upload the News Photo within 200MB")
 
 # Allows picture uploads
-uploaded_file = st.file_uploader("Pick a picture!", type=["png", "jpg", "jpeg"])
+uploaded_file = st.file_uploader("Upload the Photo below", type=["png", "jpg", "jpeg"])
 
 if uploaded_file is not None:
     # Shows the uploaded picture
@@ -44,17 +53,17 @@ if uploaded_file is not None:
 
     # Gets the picture’s description
     image_caption = generate_caption(image)
-    st.subheader("Picture Description:")
+    st.subheader("Phot Description:")
     st.write(image_caption)
 
-    # Creates a story
+    # Generate the News descriptions
     story_telling = generate_story(image_caption)
-    st.subheader("Your Story:")
+    st.subheader("The News:")
     st.write(story_telling)
 
     # Generates audio
     audio = generate_audio(story_telling)
-    if st.button("Hear Story!"):
+    if st.button("Hear the News"):
         st.audio(audio['audio'],
                  format="audio/wav",
                  start_time=0,