Create app.py

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from transformers import pipeline
+from gtts import gTTS
+import os
+
+# Function: Image to Text
+def img2text(url):
+    image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    text = image_to_text_model(url)[0]["generated_text"]
+    return text
+
+# Function: Text to Story (Placeholder)
+def text2story(text):
+    story_text = text  # Placeholder for now
+    return story_text
+
+# Function: Text to Audio
+def text2audio(story_text):
+    # Convert text to audio using gTTS
+    tts = gTTS(story_text, lang="en")
+    audio_file = "story_audio.wav"
+    tts.save(audio_file)
+    return audio_file
+
+# Streamlit App
+st.set_page_config(page_title="Your Image to Audio Story", page_icon="🦜")
+st.header("Turn Your Image to Audio Story")
+uploaded_file = st.file_uploader("Select an Image...")
+
+if uploaded_file is not None:
+    print(uploaded_file)
+    bytes_data = uploaded_file.getvalue()
+    with open(uploaded_file.name, "wb") as file:
+        file.write(bytes_data)
+    st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
+
+    # Stage 1: Image to Text
+    st.text('Processing img2text...')
+    scenario = img2text(uploaded_file.name)
+    st.write(scenario)
+
+    # Stage 2: Text to Story
+    st.text('Generating a story...')
+    story = text2story(scenario)
+    st.write(story)
+
+    # Stage 3: Story to Audio
+    st.text('Generating audio data...')
+    audio_file = text2audio(story)
+
+    # Play button
+    if st.button("Play Audio"):
+        st.audio(audio_file, format="audio/wav")