fix: prediction parsing.

app.py

@@ -112,7 +112,7 @@ def infer(video_file):
     with torch.no_grad():
         outputs = MODEL(**inputs)
         logits = outputs.logits
-    softmax_scores = torch.nn.functional.softmax(logits, dim=0)
+    softmax_scores = torch.nn.functional.softmax(logits, dim=0).squeeze(0)
     confidences = {LABELS[i]: float(softmax_scores[i]) for i in range(len(LABELS))}
     return confidences