Update data_extraction.py

data_extraction.py

@@ -271,14 +271,16 @@ def train_val_split(examples, val_fraction, seed):
 def write_jsonl(path, rows):
     with open(path, "w", encoding="utf-8") as fh:
         for row in rows:
-            fh.write(json.dumps(row, ensure_ascii=False) + "\n")
+            output_row = {k: v for k, v in row.items() if k != "field"}
+            fh.write(json.dumps(output_row, ensure_ascii=False) + "\n")
 
 
 def write_csv(path, pairs):
     with open(path, "w", newline="", encoding="utf-8") as fh:
-        writer = csv.DictWriter(fh, fieldnames=["field", "urdu", "roman"])
+        writer = csv.DictWriter(fh, fieldnames=["urdu", "roman"])
         writer.writeheader()
-        writer.writerows(pairs)
+        for p in pairs:
+            writer.writerow({"urdu": p["urdu"], "roman": p["roman"]})
 
 
 # --------------------------------------------------------------------------