Update app.py

app.py

@@ -144,7 +144,7 @@ overlap_frame_len = 16
 @spaces.GPU
 @torch.no_grad()
 @torch.inference_mode()
-def voice_conversion(source, target, diffusion_steps, length_adjust, inference_cfg_rate, f0_condition, auto_f0_adjust, pitch_shift):
+def voice_conversion(source, nonoo, target, diffusion_steps, length_adjust, inference_cfg_rate, f0_condition, auto_f0_adjust, pitch_shift):
     inference_module = model if not f0_condition else model_f0
     mel_fn = to_mel if not f0_condition else to_mel_f0
     bigvgan_fn = bigvgan_model if not f0_condition else bigvgan_44k_model
@@ -696,6 +696,7 @@ if __name__ == "__main__":
     
     inputs = [
         gr.Audio(type="filepath", label="元音声"),
+        gr.Gallery(label="ギャラリー", show_label=True, value=[gallery_data["sikokumetan"]["webp"]])
         gr.Audio(type="filepath", label="参考音声"),
         gr.Slider(minimum=1, maximum=200, value=10, step=1, label="拡散ステップ数", info="デフォルトは10、50～100が最適な品質"),
         gr.Slider(minimum=0.5, maximum=2.0, step=0.1, value=1.0, label="長さ調整", info="1.0未満で速度を上げ、1.0以上で速度を遅くします"),