benchmarks/rnnt/ootb/inference/pytorch/utils/preprocessing_utils.py [48:77]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        output_fpath = os.path.join(dest_dir,
                                    data['input_relpath'],
                                    output_fname)

        if not os.path.exists(output_fpath) or overwrite:
            cbn = sox.Transformer().speed(factor=s).convert(target_sr)
            cbn.build(input_fname, output_fpath)

        file_info = sox.file_info.info(output_fpath)
        file_info['fname'] = os.path.join(os.path.basename(dest_dir),
                                          data['input_relpath'],
                                          output_fname)
        file_info['speed'] = s
        output_dict['files'].append(file_info)

        if s == 1:
            file_info = sox.file_info.info(output_fpath)
            output_dict['original_duration'] = file_info['duration']
            output_dict['original_num_samples'] = file_info['num_samples']

    return output_dict


def parallel_preprocess(dataset, input_dir, dest_dir, target_sr, speed, overwrite, parallel):
    with multiprocessing.Pool(parallel) as p:
        func = functools.partial(preprocess,
                                 input_dir=input_dir, dest_dir=dest_dir,
                                 target_sr=target_sr, speed=speed, overwrite=overwrite)
        dataset = list(tqdm(p.imap(func, dataset), total=len(dataset)))
        return dataset
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



benchmarks/rnnt/ootb/train/utils/preprocessing_utils.py [47:76]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        output_fpath = os.path.join(dest_dir,
                                    data['input_relpath'],
                                    output_fname)

        if not os.path.exists(output_fpath) or overwrite:
            cbn = sox.Transformer().speed(factor=s).convert(target_sr)
            cbn.build(input_fname, output_fpath)

        file_info = sox.file_info.info(output_fpath)
        file_info['fname'] = os.path.join(os.path.basename(dest_dir),
                                          data['input_relpath'],
                                          output_fname)
        file_info['speed'] = s
        output_dict['files'].append(file_info)

        if s == 1:
            file_info = sox.file_info.info(output_fpath)
            output_dict['original_duration'] = file_info['duration']
            output_dict['original_num_samples'] = file_info['num_samples']

    return output_dict


def parallel_preprocess(dataset, input_dir, dest_dir, target_sr, speed, overwrite, parallel):
    with multiprocessing.Pool(parallel) as p:
        func = functools.partial(preprocess,
            input_dir=input_dir, dest_dir=dest_dir,
            target_sr=target_sr, speed=speed, overwrite=overwrite)
        dataset = list(tqdm(p.imap(func, dataset), total=len(dataset)))
        return dataset
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -