Update app.py

app.py

@@ -1,28 +1,36 @@
 
 from transformers import pipeline
 import streamlit as st
-#from gtts import gTTS
+from gtts import gTTS
+import tempfile
+import os
 
 # function part
 # img2text
-def img2text(img):
-    image_to_text_model = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
-    text = image_to_text_model(img)[0]["generated_text"]
-    return text
+def img2text(img_path):
+    captioner = pipeline(
+        "image-to-text", 
+        model="Salesforce/blip-image-captioning-base"
+    )
+    result = captioner(img_path)
+    return result[0]["generated_text"]
 
 # text2story
 def text2story(scenario):
-    generator = pipeline("text-generation", model="deepseek-ai/DeepSeek-V3")
-    story = generator(
-        f"Create a children's story based on: {scenario}",
-        max_length=150,
-        num_return_sequences=1
+    generator = pipeline(
+        "text-generation",
+        model="gpt2-medium", 
+        trust_remote_code=True,           
+        max_length=150,                   
+        num_return_sequences=1             
     )
-    return story[0]["generated_text"]
+    prompt = f"Create a children's story based on: {scenario}"
+    story = generator(prompt)[0]["generated_text"]
+    return story
 
 # text2audio
 def text2audio(story_text):
-    tts = gTTS(text=story_text, lang="en", slow=False)
+    tts = gTTS(text=story_text, lang="en")
     audio_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
     tts.save(audio_file.name)
     return audio_file.name
@@ -34,18 +42,17 @@ st.set_page_config(page_title="Your Image to Audio Story",
 st.header("Turn Your Image to Audio Story")
 uploaded_file = st.file_uploader("Select an Image...", type=["jpg", "png", "jpeg"])
 
-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)
+if uploaded_file:
+        temp_img = os.path.join(tempfile.gettempdir(), uploaded_file.name)
+        with open(temp_img, "wb") as f:
+            f.write(uploaded_file.getvalue())
+        
+        st.image(uploaded_file)
 
     #Stage 1: Image to Text
     st.text('Processing img2text...')
-    scenario = img2text(uploaded_file.name)
-    st.write(scenario)
+    scenario = img2text(temp_img)
+    st.write("Image Caption:", scenario)
 
     #Stage 2: Text to Story
     st.text('Generating a story...')
@@ -58,6 +65,9 @@ if uploaded_file is not None:
     audio_data =text2audio(story)
     st.subheader("Audio Story")
     st.audio(audio_path, format="audio/mp3")
+
+    os.unlink(temp_img)
+    os.unlink(audio_path)
     # Play button
     if st.button("Play Audio"):
         st.audio(audio_data['audio'],