babysor/MockingBird · error · ValueError

unknown input_layer:

Error message

unknown input_layer: 

What it means

The transformer Encoder constructor rejects input_layer values other than 'conv2d', 'conv2d6', 'conv2d8', 'linear', or None.

Source

Thrown at models/ppg_extractor/encoder/encoder.py:131

            )
        elif input_layer == "vgg2l":
            self.embed = VGG2L(idim, attention_dim)
        elif input_layer == "embed":
            self.embed = torch.nn.Sequential(
                torch.nn.Embedding(idim, attention_dim, padding_idx=padding_idx),
                pos_enc_class(attention_dim, positional_dropout_rate),
            )
        elif isinstance(input_layer, torch.nn.Module):
            self.embed = torch.nn.Sequential(
                input_layer,
                pos_enc_class(attention_dim, positional_dropout_rate),
            )
        elif input_layer is None:
            self.embed = torch.nn.Sequential(
                pos_enc_class(attention_dim, positional_dropout_rate)
            )
        else:
            raise ValueError("unknown input_layer: " + input_layer)
        self.normalize_before = normalize_before
        if positionwise_layer_type == "linear":
            positionwise_layer = PositionwiseFeedForward
            positionwise_layer_args = (
                attention_dim,
                linear_units,
                dropout_rate,
                activation,
            )
        elif positionwise_layer_type == "conv1d":
            positionwise_layer = MultiLayeredConv1d
            positionwise_layer_args = (
                attention_dim,
                linear_units,
                positionwise_conv_kernel_size,
                dropout_rate,
            )
        elif positionwise_layer_type == "conv1d-linear":

View on GitHub (pinned to 28dc5e14f1)

Solutions

1. Set input_layer to one of conv2d/conv2d6/conv2d8/linear or null
2. Check the config key is under the correct encoder section

Example fix

# before
input_layer: embed

# after
input_layer: conv2d

assert input_layer in {'conv2d','conv2d6','conv2d8','linear', None}

When it happens

Trigger: Constructing the ppg_extractor Encoder with an unrecognized input_layer value from config.

Common situations: Typos, or configs copied from newer ESPnet that supports additional input layers (e.g. 'embed').

Understand the failure class

Background: Invalid enum value errors: "Unknown type", "Invalid scope", "must be one of" — when a string is not on the library's allowed list — this error's family across 23 libraries.

Related errors

• unknown input_layer:
• unknown pos_enc_layer:
• Support only linear or conv1d.
• unknown encoder_attn_layer:
• unknown pos_enc_layer:

AI-assisted analysis of babysor/MockingBird@28dc5e14f1 (2026-08-27). Data as JSON: /api/errors/bd2ef24678bcc3e7. Report an issue: GitHub.