Update app.py

app.py

@@ -2,14 +2,17 @@ import gradio as gr
 from transformers import pipeline
 
 captioner = pipeline(model="microsoft/git-base")
+tts = pipeline(model="suno/bark-small")
 
 def predict(image):
-    return captioner(image)[0]["generated_text"]
+    text = captioner(image)[0]["generated_text"]
+    audio = tts(text)["audio"]
+    return text, audio
 
 demo = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="pil"),
-    outputs='text'
+    outputs=['text', gr.Audio()]
 )
 
 demo.launch()