Sure,

# Create a new ClearML dataset with S3 output storage
dataset = Dataset.create(
    dataset_project=cfg.PROJECT_NAME,
    dataset_name=folder_name,
    output_uri=cfg.S3_BUCKET_URI,
)

# Dictionary to store S3 URLs mapped by `id`
s3_urls = {}

# Iterate through rows to map `id` → S3 URL
for idx, row in metadata_df.iterrows():
    audio_path = row.get("stored_filename")  # Ensure column exists
    if not isinstance(audio_path, str) or not audio_path.strip():
        print(f"Skippi...

@<1523701070390366208:profile|CostlyOstrich36>