codec/scripts/download_lj.py

import soundfile as sf
from datasets import load_dataset

dataset = load_dataset("keithito/lj_speech", split="train")
print(dataset)
for i, x in enumerate(dataset):
    audio = x["audio"]
    wav, sr = audio["array"], audio["sampling_rate"]
    sf.write(f"ljspeech/{i}.wav", wav, sr)