Update app.py

app.py

@@ -16,10 +16,11 @@ headers = {"Authorization": f"Bearer {os.getenv('HF_TOKEN')}"}
 
 def generate_caption(image):
     pixel_values = feature_extractor(images=image, return_tensors="pt").pixel_values
-    output_ids = caption_model.generate(pixel_values, max_length=50, num_beams=4)
+    output_ids = caption_model.generate(pixel_values, max_length=50)  # <- ✅ beam search 제거
     caption = tokenizer.decode(output_ids[0], skip_special_tokens=True)
     return caption
 
+
 def tts_audio(text):
     payload = {"inputs": text}
     response = requests.post(CHAT_TTS_API, headers=headers, json=payload)