speechbrain/run_eval.py [137:167]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        for _ in tqdm(warmup_dataset, desc="Warming up..."):
            continue

    dataset = data_utils.load_data(args)
    if args.max_eval_samples is not None and args.max_eval_samples > 0:
        print(f"Subsampling dataset to first {args.max_eval_samples} samples!")
        if args.streaming:
            dataset = dataset.take(args.max_eval_samples)
        else:
            dataset = dataset.select(range(min(args.max_eval_samples, len(dataset))))
    dataset = data_utils.prepare_data(dataset)

    dataset = dataset.map(
        benchmark, batch_size=args.batch_size, batched=True, remove_columns=["audio"],
    )

    all_results = {
        "audio_length_s": [],
        "transcription_time_s": [],
        "predictions": [],
        "references": [],
    }
    result_iter = iter(dataset)
    for result in tqdm(result_iter, desc="Samples..."):
        for key in all_results:
            all_results[key].append(result[key])

    # Write manifest results (WER and RTFX)
    manifest_path = data_utils.write_manifest(
        all_results["references"],
        all_results["predictions"],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



transformers/run_eval.py [110:140]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        for _ in tqdm(warmup_dataset, desc="Warming up..."):
            continue

    dataset = data_utils.load_data(args)
    if args.max_eval_samples is not None and args.max_eval_samples > 0:
        print(f"Subsampling dataset to first {args.max_eval_samples} samples!")
        if args.streaming:
            dataset = dataset.take(args.max_eval_samples)
        else:
            dataset = dataset.select(range(min(args.max_eval_samples, len(dataset))))
    dataset = data_utils.prepare_data(dataset)

    dataset = dataset.map(
        benchmark, batch_size=args.batch_size, batched=True, remove_columns=["audio"],
    )

    all_results = {
        "audio_length_s": [],
        "transcription_time_s": [],
        "predictions": [],
        "references": [],
    }
    result_iter = iter(dataset)
    for result in tqdm(result_iter, desc="Samples..."):
        for key in all_results:
            all_results[key].append(result[key])

    # Write manifest results (WER and RTFX)
    manifest_path = data_utils.write_manifest(
        all_results["references"],
        all_results["predictions"],
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -