egs/librispeech/SSL/local/process_librispeech4finetune.py

#!/usr/bin/env python3
# Copyright    2021  Xiaomi Corp.        (authors: Fangjun Kuang)
#
# See ../../../../LICENSE for clarification regarding multiple authors
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import argparse
import logging
import os
from pathlib import Path
from typing import Optional

import torch
from lhotse import CutSet
from lhotse.recipes.utils import read_manifests_if_cached

from icefall.utils import str2bool

# Torch's multithreaded behavior needs to be disabled or
# it wastes a lot of CPU and slow things down.
# Do this outside of main() in case it needs to take effect
# even when we are not invoking the main (e.g. when spawning subprocesses).
torch.set_num_threads(1)
torch.set_num_interop_threads(1)


def get_args():
    parser = argparse.ArgumentParser()

    parser.add_argument(
        "--dataset",
        type=str,
        help="""Dataset parts to compute fbank. If None, we will use all""",
    )

    return parser.parse_args()


def process_wav_librispeech(
    dataset: Optional[str] = None,
):
    src_dir = Path("data/manifests")
    output_dir = Path("data/wav")

    if dataset is None:
        dataset_parts = (
            "dev-clean",
            "dev-other",
            "test-clean",
            "test-other",
            "train-clean-100",
            "train-clean-360",
            "train-other-500",
        )
    else:
        dataset_parts = dataset.split(" ", -1)

    prefix = "librispeech"
    suffix = "jsonl.gz"
    manifests = read_manifests_if_cached(
        dataset_parts=dataset_parts,
        output_dir=src_dir,
        prefix=prefix,
        suffix=suffix,
    )
    assert manifests is not None

    assert len(manifests) == len(dataset_parts), (
        len(manifests),
        len(dataset_parts),
        list(manifests.keys()),
        dataset_parts,
    )

    for partition, m in manifests.items():
        cuts_filename = f"{prefix}_cuts_{partition}.{suffix}"
        if (output_dir / cuts_filename).is_file():
            logging.info(f"{partition} already exists - skipping.")
            continue
        logging.info(f"Processing {partition}")
        cut_set = CutSet.from_manifests(
            recordings=m["recordings"],
            supervisions=m["supervisions"],
        )
        cut_set.to_file(output_dir / cuts_filename)


if __name__ == "__main__":
    formatter = "%(asctime)s %(levelname)s [%(filename)s:%(lineno)d] %(message)s"

    logging.basicConfig(format=formatter, level=logging.INFO)
    args = get_args()
    logging.info(vars(args))
    process_wav_librispeech(
        dataset=args.dataset,
    )