torchaudio/models/wav2vec2/model.py [350:370]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if extractor_conv_layer_config is None:
        extractor_conv_layer_config = [(512, 10, 5)] + [(512, 3, 2)] * 4 + [(512, 2, 2)] * 2

    feature_extractor = components._get_feature_extractor(
        extractor_mode, extractor_conv_layer_config, extractor_conv_bias
    )
    encoder = components._get_encoder(
        in_features=extractor_conv_layer_config[-1][0],
        embed_dim=encoder_embed_dim,
        dropout_input=encoder_projection_dropout,
        pos_conv_kernel=encoder_pos_conv_kernel,
        pos_conv_groups=encoder_pos_conv_groups,
        num_layers=encoder_num_layers,
        num_heads=encoder_num_heads,
        attention_dropout=encoder_attention_dropout,
        ff_interm_features=encoder_ff_interm_features,
        ff_interm_dropout=encoder_ff_interm_dropout,
        dropout=encoder_dropout,
        layer_norm_first=encoder_layer_norm_first,
        layer_drop=encoder_layer_drop,
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



torchaudio/models/wav2vec2/model.py [917:937]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    if extractor_conv_layer_config is None:
        extractor_conv_layer_config = [(512, 10, 5)] + [(512, 3, 2)] * 4 + [(512, 2, 2)] * 2

    feature_extractor = components._get_feature_extractor(
        extractor_mode, extractor_conv_layer_config, extractor_conv_bias
    )
    encoder = components._get_encoder(
        in_features=extractor_conv_layer_config[-1][0],
        embed_dim=encoder_embed_dim,
        dropout_input=encoder_projection_dropout,
        pos_conv_kernel=encoder_pos_conv_kernel,
        pos_conv_groups=encoder_pos_conv_groups,
        num_layers=encoder_num_layers,
        num_heads=encoder_num_heads,
        attention_dropout=encoder_attention_dropout,
        ff_interm_features=encoder_ff_interm_features,
        ff_interm_dropout=encoder_ff_interm_dropout,
        dropout=encoder_dropout,
        layer_norm_first=encoder_layer_norm_first,
        layer_drop=encoder_layer_drop,
    )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -