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 [源代码]¶
从 HuBERT [Hsu 等人,2021] 构建 “base”
HuBERT
- 参数:
encoder_projection_dropout (float) – 请参阅
wav2vec2_model()
.encoder_attention_dropout (float) – 请参阅
wav2vec2_model()
.encoder_ff_interm_dropout (float) – 请参阅
wav2vec2_model()
.encoder_dropout (float) – 请参阅
wav2vec2_model()
.encoder_layer_drop (float) – 请参阅
wav2vec2_model()
.aux_num_out (int 或 None,可选) – 请参阅
wav2vec2_model()
.
- 返回值:
生成的模型。
- 返回类型: