torchaudio.models.wav2vec2_large¶
- torchaudio.models.wav2vec2_large(encoder_projection_dropout: float = 0.1, encoder_attention_dropout: float = 0.1, encoder_ff_interm_dropout: float = 0.1, encoder_dropout: float = 0.1, encoder_layer_drop: float = 0.1, aux_num_out: Optional[int] = None) Wav2Vec2Model [源代码]¶
从 wav2vec 2.0 构建“大型”
Wav2Vec2Model
[Baevski 等人,2020]- 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: