torchaudio.models.hubert_pretrain_xlarge

torchaudio.models.hubert_pretrain_xlarge(encoder_projection_dropout: float = 0.0, encoder_attention_dropout: float = 0.0, encoder_ff_interm_dropout: float = 0.0, encoder_dropout: float = 0.0, encoder_layer_drop: float = 0.0, mask_prob: float = 0.8, mask_channel_prob: float = 0.0, mask_channel_length: int = 10, feature_grad_mult: Optional[float] = None) → HuBERTPretrainModel

Builds “extra large” HuBERTPretrainModel from HuBERT [Hsu et al., 2021] for pretraining.

Parameters:

• encoder_projection_dropout (float) – See hubert_pretrain_model().

• encoder_attention_dropout (float) – See hubert_pretrain_model().

• encoder_ff_interm_dropout (float) – See hubert_pretrain_model().

• encoder_dropout (float) – See hubert_pretrain_model().

• encoder_layer_drop (float) – See hubert_pretrain_model().

• mask_prob (float) – See hubert_pretrain_model().

• mask_channel_prob (float) – See hubert_pretrain_model().

• mask_channel_length (int) – See hubert_pretrain_model().

• feature_grad_mult (float or None) – See hubert_pretrain_model().

Returns:

The resulting model.

Return type:

HuBERTPretrainModel