Create app.py

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import pandas as pd
+from datasets import load_dataset
+from jiwer import wer, cer, transforms
+import os
+from datetime import datetime
+
+
+transform = transforms.Compose([
+    transforms.RemovePunctuation(),
+    transforms.ToLowerCase(),
+    transforms.RemoveWhiteSpace(replace_by_space=True),
+])
+
+
+dataset = load_dataset("sudoping01/bambara-asr-benchmark", name="default")["train"]
+references = {row["id"]: row["text"] for row in dataset}
+
+
+leaderboard_file = "leaderboard.csv"
+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", "prediction"}:
+            return "Error: CSV must contain exactly 'id' and 'prediction' columns.", None
+        if df["id"].duplicated().any():
+            return "Error: Duplicate 'id's found in the CSV.", None
+        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["prediction"]
+            wers.append(wer(ref, pred, standardize=transform))
+            cers.append(cer(ref, pred, standardize=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(
+            [[submitter_name, avg_wer, avg_cer, timestamp]],
+            columns=["submitter", "WER", "CER", "timestamp"]
+        )
+        leaderboard = pd.concat([leaderboard, new_entry]).sort_values("WER")
+        leaderboard.to_csv(leaderboard_file, index=False)
+        
+        return "Submission processed successfully!", leaderboard
+    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(
+        """
+        # Bambara ASR Leaderboard
+        Upload a CSV file with 'id' and 'text' columns to evaluate your ASR predictions. 
+        The 'id's must match those in the dataset. 
+        [View the dataset here](https://huggingface.co/datasets/MALIBA-AI/bambara_general_leaderboard_dataset).
+        
+        - **WER**: Word Error Rate (lower is better).
+        - **CER**: Character Error Rate (lower is better).
+        """
+    )
+    with gr.Row():
+        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)
+    leaderboard_display = gr.DataFrame(
+        label="Leaderboard",
+        value=pd.read_csv(leaderboard_file),
+        interactive=False
+    )
+    
+    submit_btn.click(
+        fn=process_submission,
+        inputs=[submitter, csv_upload],
+        outputs=[output_msg, leaderboard_display]
+    )
+
+demo.launch()