speechbrain

/

spkrec-ecapa-voxceleb

like 179

Follow

SpeechBrain 345

When i run:

emb_model = EncoderClassifier.from_hparams(source="speechbrain/spkrec-ecapa-voxceleb")

i get this:

When i go to hyperparams.yaml, i have this in modules and pretainer:

# ...
modules:
    compute_features: !ref <compute_features>
    mean_var_norm: !ref <mean_var_norm>
    embedding_model: !ref <embedding_model>
    mean_var_norm_emb: !ref <mean_var_norm_emb>
    classifier: !ref <classifier>

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
    loadables:
        embedding_model: !ref <embedding_model>
        mean_var_norm_emb: !ref <mean_var_norm_emb>
        classifier: !ref <classifier>
        label_encoder: !ref <label_encoder>
    paths:
        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
        mean_var_norm_emb: !ref <pretrained_path>/mean_var_norm_emb.ckpt
        classifier: !ref <pretrained_path>/classifier.ckpt
        label_encoder: !ref <pretrained_path>/label_encoder.txt

Shouldn't it have a loadble for mean_var_norm and a mean_var_norm.ckpt?

I am new into the speechbrain/huggingface community and trying to understand how this repo works.
Thanks for your attention.