espnet2.train.preprocessor.TSEPreprocessor
espnet2.train.preprocessor.TSEPreprocessor
class espnet2.train.preprocessor.TSEPreprocessor(train: bool, train_spk2enroll: str | None = None, enroll_segment: int | None = None, load_spk_embedding: bool = False, load_all_speakers: bool = False, rir_scp: str | None = None, rir_apply_prob: float = 1.0, noise_scp: str | None = None, noise_apply_prob: float = 1.0, noise_db_range: str = '3_10', short_noise_thres: float = 0.5, speech_volume_normalize: float | None = None, speech_name: str = 'speech_mix', speech_ref_name_prefix: str = 'speech_ref', noise_ref_name_prefix: str = 'noise_ref', dereverb_ref_name_prefix: str = 'dereverb_ref', use_reverberant_ref: bool = False, num_spk: int = 1, num_noise_type: int = 1, sample_rate: int = 8000, force_single_channel: bool = False, channel_reordering: bool = False, categories: List | None = None, data_aug_effects: List | None = None, data_aug_num: List[int] = [1, 1], data_aug_prob: float = 0.0, speech_segment: int | None = None, avoid_allzero_segment: bool = True, flexible_numspk: bool = False)
Bases: EnhPreprocessor
Preprocessor for Target Speaker Extraction.