Update app.py

app.py

@@ -14,8 +14,7 @@ HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 def img2Text(url):
     image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
     text = image_to_text(url)[0]["generated_text"]
-    st.subheader("Caption :")
-    st.subheader(text)
+    print(text)
     return text
 
 #llm
@@ -32,8 +31,7 @@ def generate_story(scenario):
         model_name="gpt-3.5-turbo", temperature=1), prompt=prompt, verbose=True)
 
     story = story_llm.predict(scenario=scenario)
-    st.subheader("Story :")
-    st.subheader(story)
+    print(story)
     return story
 
 #textToSpeech
@@ -55,4 +53,30 @@ def text2Speech(story) :
 
 scenario = img2Text("photo.jpg")
 story = generate_story(scenario)
-text2Speech(story)
+text2Speech(story)
+
+def main()
+    st.set_page_config(page_title="Image to Short Story", page_icon="")
+    st.header("Turn img into Audio Story")
+    uploaded_file = st.file.uploader("Choose an image(jpg type)", type="jpg")
+    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)
+        scenario = img2Text(uploaded_file.name)
+        story = generate_story(scenario)
+        text2Speech(story)
+
+        with st.expander("scenario")
+            st.write(scenario)
+        with st.expander("story")
+            st.write(story)
+
+        st.audio("audio.flac")
+
+
+if _name_ == '_main_';
+    main()