default inputs

app.py

@@ -60,13 +60,12 @@ net, feature_utils, seq_cfg = get_model()
 
 @spaces.GPU(duration=120)
 @torch.inference_mode()
-def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str, num_steps: 25,
-                   cfg_strength: 4.5, duration: 8.0):
-
+def video_to_audio(video: gr.Video, prompt: str, negative_prompt: str):
+    
+    num_steps = 25
+    cfg_strength = 4.5
+    duration = 8.0
     rng = torch.Generator(device=device)
-    # if seed >= 0:
-    #     rng.manual_seed(seed)
-    # else:
     rng.seed()
 
     fm = FlowMatching(min_sigma=0, inference_mode='euler', num_steps=num_steps)
@@ -120,7 +119,7 @@ video_to_audio_tab = gr.Interface(
     ],
     outputs='playable_video',
     cache_examples=False,
-    title='Sonisphere — Sonic Branding with Multi-modal Audio Synthesis',
+    title='Sonisphere — Sonic Branding through Multi-modal Audio Synthesis',
     examples=[
     ])