Update app.py

app.py

@@ -38,7 +38,12 @@ def text_to_audio_file(text):
 
     return tmp_path
 
-
+def generate_caption_from_image(model, processor, image):
+    # image: PIL.Image
+    inputs = processor(images=image, return_tensors="pt")
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
 # -------------------------------
 # Gradio interface: Caption + Audio
 # -------------------------------