Update app.py

app.py

@@ -100,7 +100,7 @@ def model_generate_ans(img=None,img_audio=None,val_q=None):
             next_token_embeds = phi_model.model.embed_tokens(predicted_word_token) # 4,1,2560
             val_combined_embeds   = torch.cat([val_combined_embeds, next_token_embeds], dim=1)
             
-        predicted_captions_decoded = tokenizer.batch_decode(predicted_caption,ignore_index = 50256)
+        predicted_captions_decoded = tokenizer.batch_decode(predicted_caption,ignore_index = 50256)[0]
     
     return predicted_captions_decoded