Upload app.py with huggingface_hub

app.py

@@ -38,28 +38,28 @@ print("📄 Files:", [p.name for p in LOCAL_DATA_DIR.iterdir()])
 # =========================
 
 OMNI_MLLM_RENAME = {
-    "Task1-1": "Image Understanding",
-    "Task1-2": "Video Understanding",
-
-    "Task2-1": "Speech-Driven Image Understanding",
-    "Task2-2": "Image-Audio Reasoning",
-    "Task2-3": "Speech-Based Image QA",
-    "Task2-4": "Speech Generation from Image",
-    "Task2-5": "Audio Matching from Image",
-
-    "Task3-1": "Speech-Driven Video Understanding",
-    "Task3-2": "Video-Audio Reasoning",
-    "Task3-3": "Speech-Based Video QA",
-    "Task3-4": "Speech Generation from Video",
-    "Task3-5": "Audio Matching from Video",
-    "Task3-6": "Next-Action Prediction",
+    "Task1-1": "Image\nUnderstanding",
+    "Task1-2": "Video\nUnderstanding",
+
+    "Task2-1": "Speech-Driven\nImage Understanding",
+    "Task2-2": "Image-Audio\nReasoning",
+    "Task2-3": "Speech-Based\nImage QA",
+    "Task2-4": "Speech Generation\nfrom Image",
+    "Task2-5": "Audio Matching\nfrom Image",
+
+    "Task3-1": "Speech-Driven\nVideo Understanding",
+    "Task3-2": "Video-Audio\nReasoning",
+    "Task3-3": "Speech-Based\nVideo QA",
+    "Task3-4": "Speech Generation\nfrom Video",
+    "Task3-5": "Audio Matching\nfrom Video",
+    "Task3-6": "Next-Action\nPrediction",
 }
 
 IMAGE_GEN_RENAME = {
     "WIScore": "WIScore",
-    "SC": "Semantic Consistency",
-    "PQ": "Perceptual Quality",
-    "OR": "Overall Quality",
+    "SC": "Semantic\nConsistency",
+    "PQ": "Perceptual\nQuality",
+    "OR": "Overall\nQuality",
 }
 
 VIDEO_GEN_RENAME = {