Update app.py

app.py

@@ -8,59 +8,59 @@ def process_video(audio_file, video_file):
     audio_path = audio_file.name
     video_path = video_file.name
     out_path = "output_video.mp4"
-
+    
     # Save uploaded files
     audio_file.save(audio_path)
     video_file.save(video_path)
-
+    
     # Define command flags
     sample_mode = "cross"  # or "reconstruction"
     generate_from_filelist = 0
     model_path = "checkpoints/checkpoint.pt"
     pads = "0,0,0,0"
-
+    
     if sample_mode == "reconstruction":
         sample_input_flags = "--sampling_input_type=first_frame --sampling_ref_type=first_frame"
     elif sample_mode == "cross":
         sample_input_flags = "--sampling_input_type=gt --sampling_ref_type=gt"
     else:
         return "Error: sample_mode can only be \"cross\" or \"reconstruction\""
-
+    
     MODEL_FLAGS = "--attention_resolutions 32,16,8 --class_cond False --learn_sigma True --num_channels 128 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm False"
     DIFFUSION_FLAGS = "--predict_xstart False --diffusion_steps 1000 --noise_schedule linear --rescale_timesteps False"
     SAMPLE_FLAGS = f"--sampling_seed=7 {sample_input_flags} --timestep_respacing ddim25 --use_ddim True --model_path={model_path}"
     DATA_FLAGS = "--nframes 5 --nrefer 1 --image_size 128 --sampling_batch_size=32"
     TFG_FLAGS = "--face_hide_percentage 0.5 --use_ref=True --use_audio=True --audio_as_style=True"
     GEN_FLAGS = f"--generate_from_filelist {generate_from_filelist} --video_path={video_path} --audio_path={audio_path} --out_path={out_path} --save_orig=False --face_det_batch_size 16 --pads {pads} --is_voxceleb2=False"
-
+    
     # Combine all flags into one command
     command = f"python your_model_script.py {MODEL_FLAGS} {DIFFUSION_FLAGS} {SAMPLE_FLAGS} {DATA_FLAGS} {TFG_FLAGS} {GEN_FLAGS}"
-
-    # Execute the command
+    
     try:
         subprocess.run(command, shell=True, check=True)
         return out_path
     except subprocess.CalledProcessError as e:
         return f"Error processing video: {e}"
-
-    # Clean up the files after processing
-    os.remove(audio_path)
-    os.remove(video_path)
-
-    # Delete output video after sending to the user
-    os.remove(out_path)
+    finally:
+        # Clean up the files after processing
+        if os.path.exists(audio_path):
+            os.remove(audio_path)
+        if os.path.exists(video_path):
+            os.remove(video_path)
+        if os.path.exists(out_path):
+            os.remove(out_path)
 
 # Create a Gradio interface
 iface = gr.Interface(
     fn=process_video,
     inputs=[
-        gr.inputs.Audio(label="Input Audio", type="file"),
-        gr.inputs.Video(label="Input Video", type="file")
+        gr.Audio(label="Input Audio"),  # Updated syntax
+        gr.Video(label="Input Video")   # Updated syntax
     ],
-    outputs=gr.outputs.Video(label="Processed Video"),
+    outputs=gr.Video(label="Processed Video"),  # Updated syntax
     title="Audio-Video Processing",
     description="Upload an audio file and a video file to process the video based on the audio input."
 )
 
 # Launch the interface
-iface.launch()
+iface.launch()