Update app.py

app.py

@@ -5,7 +5,7 @@ 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")
+story_pipeline = pipeline("text-generation", model="Qwen/Qwen2.5-0.5B-Instruct")
 
 
 def extract_image_caption(image_data):
@@ -24,7 +24,7 @@ def compose_story_from_caption(caption_detail):
             f"Image Details: {caption_detail}\n\nStory:"
         )
         
-        story_results = story_pipeline(prompt_text, num_return_sequences=1, max_length=150)
+        story_results = story_pipeline(prompt_text, num_return_sequences=1, max_new_tokens=150)
         story_text = story_results[0]['generated_text']
         
         # 提取故事
@@ -33,9 +33,7 @@ def compose_story_from_caption(caption_detail):
         else:
             story = story_text.strip()
         
-        # 检查长度
-        if 80 <= len(story.split()) <= 100:
-            return story
+        return story
     
 def convert_text_to_audio(text_content, audio_path="output.mp3"):
     """