Update app.py

app.py

@@ -1,6 +1,9 @@
 import streamlit as st
 from transformers import BlipProcessor, BlipForConditionalGeneration
 from PIL import Image
+from gtts import gTTS
+import tempfile
+import os
 
 # 加载BLIP模型和处理器
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
@@ -25,3 +28,17 @@ if image_data is not None:
     caption = processor.decode(out[0], skip_special_tokens=True)
     
     st.write(f"图像描述: {caption}")
+    
+    # 生成语音
+    tts = gTTS(text=caption, lang='zh')
+    
+    # 创建临时文件来保存音频
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as fp:
+        tts.save(fp.name)
+        audio_file = fp.name
+    
+    # 在Streamlit中播放音频
+    st.audio(audio_file)
+
+    # 删除临时文件
+    os.remove(audio_file)