voxlingua107-epaca-tdnn-ce / hyperparams.yaml
Tanel's picture
First model version
a5a2e80
pretrained_path: TalTechNLP/voxlingua107-epaca-tdnn-ce
# Feature parameters
n_mels: 60
left_frames: 0
right_frames: 0
deltas: false
# Number of speakers
out_n_neurons: 107
# Functions
compute_features: !new:speechbrain.lobes.features.Fbank
n_mels: 60
left_frames: 0
right_frames: 0
deltas: false
embedding_model: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
input_size: 60
channels: [1024, 1024, 1024, 1024, 3072]
kernel_sizes: [5, 3, 3, 3, 1]
dilations: [1, 2, 3, 4, 1]
attention_channels: 128
lin_neurons: 256
classifier: !new:speechbrain.lobes.models.Xvector.Classifier
input_shape: [null, null, 256]
activation: !name:torch.nn.LeakyReLU
lin_blocks: 1
lin_neurons: 512
out_neurons: !ref <out_n_neurons>
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
norm_type: sentence
std_norm: false
modules:
compute_features: !ref <compute_features>
mean_var_norm: !ref <mean_var_norm>
embedding_model: !ref <embedding_model>
classifier: !ref <classifier>
label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
loadables:
embedding_model: !ref <embedding_model>
classifier: !ref <classifier>
label_encoder: !ref <label_encoder>
paths:
embedding_model: !ref <pretrained_path>/embedding_model.ckpt
classifier: !ref <pretrained_path>/classifier.ckpt
label_encoder: !ref <pretrained_path>/label_encoder.txt