diff --git a/paddlespeech/vector/exps/ge2e/speaker_verification_dataset.py b/paddlespeech/vector/exps/ge2e/speaker_verification_dataset.py index 87b7d59a3..ae2c9427f 100644 --- a/paddlespeech/vector/exps/ge2e/speaker_verification_dataset.py +++ b/paddlespeech/vector/exps/ge2e/speaker_verification_dataset.py @@ -39,7 +39,12 @@ class MultiSpeakerMelDataset(Dataset): def __init__(self, dataset_root: Path): self.root = Path(dataset_root).expanduser() - speaker_dirs = [f for f in self.root.glob("*") if f.is_dir()] + speaker_dirs = [] + for f in self.root.glob("*"): + if f.is_dir(): + assert list(f.glob( + "*.npy")), "This folder NOT includes any npy data file." + speaker_dirs.append(f) speaker_utterances = { speaker_dir: list(speaker_dir.glob("*.npy"))