Update app.py

app.py

@@ -8,19 +8,14 @@ import re
 
 from huggingface_hub import login
 
-
 token = os.environ.get("HG_TOKEN")
 
-print(f"Token exists: {token is not None}")
-
 login(token)
 
-# Load the Bambara ASR dataset
 print("Loading dataset...")
 dataset = load_dataset("sudoping01/bambara-speech-recognition-benchmark", name="default")["eval"]
 references = {row["id"]: row["text"] for row in dataset}
 
-# Load or initialize the leaderboard
 leaderboard_file = "leaderboard.csv"
 if not os.path.exists(leaderboard_file):
     pd.DataFrame(columns=["submitter", "WER", "CER", "timestamp"]).to_csv(leaderboard_file, index=False)
@@ -41,11 +36,11 @@ def normalize_text(text):
     # Convert to lowercase
     text = text.lower()
     
-    # Remove punctuation, keeping spaces
-    text = re.sub(r'[^\w\s]', '', text)
+    # # Remove punctuation, keeping spaces
+    # text = re.sub(r'[^\w\s]', '', text)
     
-    # Normalize whitespace
-    text = re.sub(r'\s+', ' ', text).strip()
+    # # Normalize whitespace
+    # text = re.sub(r'\s+', ' ', text).strip()
     
     return text