local/check_librispeech.py

import os
from pathlib import Path

import pandas as pd
from tqdm import tqdm

from audiozen.acoustics.io import load_audio


librispeech_metadata_fpath = Path(
    "/home/xhao/proj/audiozen/recipes/librimix_sot/local/metadata/LibriSpeech/train-clean-100.csv"
).resolve()
librispeech_metadata = pd.read_csv(librispeech_metadata_fpath, engine="python")

librispeech_dir = Path("/nfs/xhao/data/LibriSpeech").resolve()

for index, row in tqdm(librispeech_metadata.iterrows()):
    origin_path = row["origin_path"]
    origin_path = librispeech_dir / origin_path
    assert os.path.exists(origin_path)
    y, sr = load_audio(origin_path)
    assert sr == 16000