Create app.py

app.py

@@ -0,0 +1,36 @@
+import streamlit as st
+from PIL import Image
+import time
+from transformers import pipeline
+
+# Load models once at startup
+@st.cache_resource
+def load_models():
+    caption_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+    text_model = pipeline("text-generation", model="distilbert/distilgpt2")
+    speech_model = pipeline("text-to-speech", model="facebook/mms-tts-eng")
+    return caption_model, text_model, speech_model
+
+caption, generator, speech = load_models()
+
+# App title
+st.title("Streamlit Demo on Hugging Face")
+st.write("Welcome to the app!")
+
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
+
+if uploaded_image is not None:
+    image = Image.open(uploaded_image)
+    st.image(image, caption="Uploaded Image")
+    
+    with st.spinner("Generating caption..."):
+        caption_result = caption(image, max_length=30)
+        st.write("Image Caption:", caption_result[0]['generated_text'])
+    
+    with st.spinner("Generating story..."):
+        story = generator(caption_result[0]['generated_text'], max_length=100)
+        st.write("Generated Story:", story[0]['generated_text'])
+    
+    with st.spinner("Generating speech..."):
+        speech_output = speech(story[0]['generated_text'])
+        st.audio(speech_output["audio"], sample_rate=speech_output["sampling_rate"])