torchaudio.models.wav2vec2_xlsr_2b¶
- torchaudio.models.wav2vec2_xlsr_2b(encoder_projection_dropout: float = 0.1, encoder_attention_dropout: float = 0.0, encoder_ff_interm_dropout: float = 0.0, encoder_dropout: float = 0.0, encoder_layer_drop: float = 0.0, aux_num_out: Optional[int] = None) Wav2Vec2Model[source]¶
Builds XLS-R model [Babu et al., 2021] with 2 billions of parameters. The architecture is compatible with Wav2Vec2 model [Baevski et al., 2020], and so the output class is
Wav2Vec2Model.- Parameters:
encoder_projection_dropout (float) – See
wav2vec2_model().encoder_attention_dropout (float) – See
wav2vec2_model().encoder_ff_interm_dropout (float) – See
wav2vec2_model().encoder_dropout (float) – See
wav2vec2_model().encoder_layer_drop (float) – See
wav2vec2_model().aux_num_out (int, optional) – See
wav2vec2_model().
- Returns:
The resulting model.
- Return type:
