Update app.py

app.py

@@ -5,7 +5,7 @@ from jiwer import wer, cer, transforms
 import os
 from datetime import datetime
 
-
+# Define text normalization transform
 transform = transforms.Compose([
     transforms.RemovePunctuation(),
     transforms.ToLowerCase(),
@@ -22,9 +22,8 @@ if not os.path.exists(leaderboard_file):
     pd.DataFrame(columns=["submitter", "WER", "CER", "timestamp"]).to_csv(leaderboard_file, index=False)
 
 def process_submission(submitter_name, csv_file):
-
     try:
-        # Read and validate the uploaded CSV
+
         df = pd.read_csv(csv_file)
         if set(df.columns) != {"id", "text"}:
             return "Error: CSV must contain exactly 'id' and 'text' columns.", None
@@ -33,19 +32,19 @@ def process_submission(submitter_name, csv_file):
         if set(df["id"]) != set(references.keys()):
             return "Error: CSV 'id's must match the dataset 'id's.", None
         
-        # Calculate WER and CER for each prediction
+
         wers, cers = [], []
         for _, row in df.iterrows():
             ref = references[row["id"]]
             pred = row["text"]
-            wers.append(wer(ref, pred, standardize=transform))
-            cers.append(cer(ref, pred, standardize=transform))
+            wers.append(wer(ref, pred, truth_transform=transform, hypothesis_transform=transform))
+            cers.append(cer(ref, pred, truth_transform=transform, hypothesis_transform=transform))
         
-        # Compute average WER and CER
+   
         avg_wer = sum(wers) / len(wers)
         avg_cer = sum(cers) / len(cers)
         
-        # Update the leaderboard
+    
         leaderboard = pd.read_csv(leaderboard_file)
         timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
         new_entry = pd.DataFrame(
@@ -59,7 +58,7 @@ def process_submission(submitter_name, csv_file):
     except Exception as e:
         return f"Error processing submission: {str(e)}", None
 
-# Create the Gradio interface
+
 with gr.Blocks(title="Bambara ASR Leaderboard") as demo:
     gr.Markdown(
         """
@@ -73,7 +72,7 @@ with gr.Blocks(title="Bambara ASR Leaderboard") as demo:
         """
     )
     with gr.Row():
-        submitter = gr.Textbox(label="Submitter Name or Model Name", placeholder="e.g.,  MALIBA-AI/asr")
+        submitter = gr.Textbox(label="Submitter Name or Model Name", placeholder="e.g., MALIBA-AI/asr")
         csv_upload = gr.File(label="Upload CSV File", file_types=[".csv"])
     submit_btn = gr.Button("Submit")
     output_msg = gr.Textbox(label="Status", interactive=False)