Create app.py

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import os 
+import subprocess
+import tempfile
+from glob import glob
+
+def run_inference(image_input, audio_input):
+
+    # Create a temporary folder for downloaded and processed images
+    temp_dir = tempfile.mkdtemp()
+
+    try:
+        # Run the inference command
+        python inference.py --config configs/inference.yaml --input_image <IMAGE_PATH> --input_audio <AUDIO_PATH> --output_dir <SAVE_PATH>
+        
+        subprocess.run(
+            [
+                "python", "inference.py",
+                "--config", "configs/inference.yaml",
+                f"input_image={image_input}",
+                f"input_audio={audio_input}",
+                f"output_dir={temp_dir}",
+            ],
+            check=True
+        )
+
+        # Collect the output images
+        output_video = glob(os.path.join(temp_dir, "*.mp4"))
+        return output_video[0]
+    except subprocess.CalledProcessError as e:
+        raise gr.Error(f"Error during inference: {str(e)}")
+
+with gr.Blocks() as demo:
+    with gr.Column():
+        gr.Markdown("# MEMO")
+        with gr.Row():
+            with gr.Column():
+                image_input = gr.Image(label="Image Input", type="filepath")
+                audio_input = gr.Audio(label="Audio Input")
+                submit_btn = gr.Button("Submit")
+            with gr.Column():
+                output_result = gr.Video(label="Result")
+
+    submit_btn.click(
+        fn =run_inference,
+        inputs =[image_input, audio_input],
+        outputs = [output_result]
+    )
+
+demo.queue().launch()