babysor/MockingBird · error

No model yaml config found for convertor

Error message

No model yaml config found for convertor

What it means

Error "No model yaml config found for convertor" thrown in babysor/MockingBird.

Source

Thrown at models/ppg2mel/__init__.py:198

        bottle_neck_features = self.reduce_proj(bottle_neck_features)

        ## Decoder
        if bottle_neck_features.size(0) > 1:
            mel_outputs, alignments = self.decoder.inference_batched(bottle_neck_features)
        else:
            mel_outputs, alignments = self.decoder.inference(bottle_neck_features,)
        ## Post-processing
        mel_outputs_postnet = self.postnet(mel_outputs.transpose(1, 2)).transpose(1, 2)
        mel_outputs_postnet = mel_outputs + mel_outputs_postnet
        # outputs = mel_outputs_postnet[0]
        
        return mel_outputs[0], mel_outputs_postnet[0], alignments[0]

def load_model(model_file, device=None):
    # search a config file
    model_config_fpaths = list(model_file.parent.rglob("*.yaml"))
    if len(model_config_fpaths) == 0:
        raise "No model yaml config found for convertor"
    if device is None:
        device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

    model_config = HpsYaml(model_config_fpaths[0])
    ppg2mel_model = MelDecoderMOLv2(
        **model_config["model"]
    ).to(device)
    ckpt = torch.load(model_file, map_location=device)
    ppg2mel_model.load_state_dict(ckpt["model"])
    ppg2mel_model.eval()
    return ppg2mel_model

View on GitHub (pinned to 28dc5e14f1)

When it happens

Trigger: Thrown at models/ppg2mel/__init__.py:198 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of babysor/MockingBird@28dc5e14f1 (2026-08-27). Data as JSON: /api/errors/3a7bf3f315da74d6. Report an issue: GitHub.