Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,61 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+from transformers import pipeline
+from PIL import Image
+
+# Creates a brief description for the pictures
+def generate_caption(image):
+    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-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("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 audio
+def generate_audio(story):
+    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 to generate the audio
+
+# Displays the title
+st.title("Tool for the Reporter - Turning the News Photo into Audio")
+
+# Describes the app for users
+st.write("Please upload the News Photo within 200MB")
+
+# Allows picture uploads
+uploaded_file = st.file_uploader("Upload the Photo below", type=["png", "jpg", "jpeg"])
+
+if uploaded_file is not None:
+    # Shows the uploaded picture
+    image = Image.open(uploaded_file)
+    st.image(image, caption="Your Picture!", use_container_width=True)
+
+    # Gets the picture’s description
+    image_caption = generate_caption(image)
+    st.subheader("Phot Description:")
+    st.write(image_caption)
+
+    # Generate the News descriptions
+    story_telling = generate_story(image_caption)
+    st.subheader("The News:")
+    st.write(story_telling)
+
+    # Generates audio
+    audio = generate_audio(story_telling)
+    if st.button("Hear the News"):
+        st.audio(audio['audio'],
+                 format="audio/wav",
+                 start_time=0,
+                 sample_rate=audio['sampling_rate'])