fairseq/examples/textless_nlp/gslm/speech2unit/clustering/utils.py

# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

from typing import List, Tuple


def get_audio_files(manifest_path: str) -> Tuple[str, List[str], List[int]]:
    fnames, sizes = [], []
    with open(manifest_path, "r") as f:
        root_dir = f.readline().strip()
        for line in f:
            items = line.strip().split("\t")
            assert (
                len(items) == 2
            ), f"File must have two columns separated by tab. Got {line}"
            fnames.append(items[0])
            sizes.append(int(items[1]))
    return root_dir, fnames, sizes