torchaudio.models.hubert_pretrain_large¶
- torchaudio.models.hubert_pretrain_large(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[原始碼]¶
從 HuBERT [Hsu et al.，2021] 建構用於預訓練的「大型」
HuBERTPretrainModel。- 參數:
encoder_projection_dropout (float) – 請參閱
hubert_pretrain_model()。encoder_attention_dropout (float) – 請參閱
hubert_pretrain_model()。encoder_ff_interm_dropout (float) – 請參閱
hubert_pretrain_model()。encoder_dropout (float) – 請參閱
hubert_pretrain_model()。encoder_layer_drop (float) – 請參閱
hubert_pretrain_model()。mask_prob (float) – 請參閱
hubert_pretrain_model()。mask_channel_prob (float) – 請參閱
hubert_pretrain_model()。mask_channel_length (int) – 請參閱
hubert_pretrain_model()。feature_grad_mult (float 或 None) – 請參閱
hubert_pretrain_model()。
- 返回:
產生的模型。
- 返回類型:
