torchaudio.models.hubert_base¶
- torchaudio.models.hubert_base(encoder_projection_dropout: float = 0.1, encoder_attention_dropout: float = 0.1, encoder_ff_interm_dropout: float = 0.0, encoder_dropout: float = 0.1, encoder_layer_drop: float = 0.05, aux_num_out: Optional[int] = None) Wav2Vec2Model [原始碼]¶
從 HuBERT [Hsu et al., 2021] 建構「base」
HuBERT
- 參數:
encoder_projection_dropout (float) – 請參閱
wav2vec2_model()
。encoder_attention_dropout (float) – 請參閱
wav2vec2_model()
。encoder_ff_interm_dropout (float) – 請參閱
wav2vec2_model()
。encoder_dropout (float) – 請參閱
wav2vec2_model()
。encoder_layer_drop (float) – 請參閱
wav2vec2_model()
。aux_num_out (int 或 None, 選填) – 請參閱
wav2vec2_model()
。
- 回傳:
產生的模型。
- 回傳類型: