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[源]¶
根據 HuBERT [Hsu et al., 2021] 構建用於預訓練的“large”
HuBERTPretrainModel模型。- 引數:
encoder_projection_dropout (float) – 請參見
hubert_pretrain_model()。encoder_attention_dropout (float) – 請參見
hubert_pretrain_model()。encoder_ff_interm_dropout (float) – 請參見
hubert_pretrain_model()。encoder_dropout (float) – 請參見
hubert_pretrain_model()。encoder_layer_drop (float) – 請參見
hubert_pretrain_model()。mask_prob (float) – 請參見
hubert_pretrain_model()。mask_channel_prob (float) – 請參見
hubert_pretrain_model()。mask_channel_length (int) – 請參見
hubert_pretrain_model()。feature_grad_mult (float 或 None) – 請參見
hubert_pretrain_model()。
- 返回值:
生成的模型。
- 返回型別:
