Update app.py

app.py

@@ -4,20 +4,14 @@ from transformers import pipeline
 from gtts import gTTS
 
 st.set_page_config(page_title="Image to Audio Story", page_icon="🦜")
+caption_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+story_pipeline = pipeline("text-generation", model="Qwen/Qwen2-1.5B")
 
 
 def extract_image_caption(image_data):
-    """
-    利用预训练模型从图像中提取描述性文字。
-    """
     img_obj = Image.open(image_data)
-    caption_pipeline = pipeline(
-        "image-to-text",
-        model="Salesforce/blip-image-captioning-base",
-    )
     caption_results = caption_pipeline(img_obj)
-    caption_text = caption_results[0]['generated_text']
-    return caption_text
+    return caption_results[0]['generated_text']
 
 
 def compose_story_from_caption(caption_detail):