Update app.py

app.py

@@ -1,6 +1,11 @@
 import streamlit as st
 from transformers import pipeline
 
+
+
+
+
+
 st.set_page_config(page_title="Your Image to Audio Story",
                    page_icon="🦜")
 st.header("Turn Your Image to Audio Story")
@@ -14,29 +19,34 @@ if uploaded_file is not None:
     st.image(uploaded_file, caption="Uploaded Image",
              use_column_width=True)
 
-    #Stage 1: Image to Text
-    def img2text(imgname):
+    #Define function:  
+    def img2txt(imgname):
         pipe = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning")
         scenario = pipe(imgname)
-        return scenario  
-    st.text('Processing img2text...')
-    scenario = img2text(uploaded_file.name)
-    st.write(scenario)
+        return scenario[0]['generated_text']  
 
-    #Stage 2: Text to Story
     def txt2story(txtname):
         pipe = pipeline("text-generation", model="openai-community/gpt2")
         story = pipe(txtname)
-        return story   
-    st.text('Generating a story...')
-    story = txt2story(scenario)
-    st.write(story)
+        return story[0]["generated_text"] 
 
-    #Stage 3: Story to Audio data
     def text2audio(textname):
         pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")
         audio_data = pipe(textname)
-        return audio_data     
+        return audio_data  
+
+    #Stage 1: Image to Text    
+    st.text('Processing img2text...')
+    scenario = img2txt(uploaded_file.name)
+    st.write(scenario)
+
+    #Stage 2: Text to Story
+  
+    st.text('Generating a story...')
+    story = txt2story(scenario)
+    st.write(story)
+
+    #Stage 3: Story to Audio data  
     st.text('Generating audio data...')
     audio_data =text2audio(story)