Create app.py

app.py

@@ -0,0 +1,19 @@
+import os
+import gradio as gr
+from transformers import pipeline
+
+pipe = pipeline("image-to-text",
+                model="./models/Salesforce/blip-image-captioning-base")
+tts_pipe = pipeline("text-to-speech",
+                    model="./models/kakao-enterprise/vits-ljs")
+
+def launch(input):
+    out = pipe(input)
+    return out[0]['generated_text']
+
+iface = gr.Interface(launch,
+                     inputs=gr.Image(type='pil'),
+                     outputs="text")
+iface.lauch()
+
+