File size: 1,450 Bytes
fbf1e1b d53daf9 c0746be d53daf9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 |
# CNN14 pre-trained on VGGSound with supervised objective
# Feature parameters
n_mels: 80
# Pretrain folder (HuggingFace)
pretrained_path: Ubenwa/sb-cssl-vgg-sup
# Output parameters
out_n_neurons: 308
# Model params
compute_features: !new:speechbrain.lobes.features.Fbank
n_mels: 80
left_frames: 0
right_frames: 0
deltas: false
sample_rate: 16000
n_fft: 400
win_length: 25
hop_length: 10
f_min: 0
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
norm_type: sentence
std_norm: False
embedding_model: !new:crytorch.models.components.pann.Cnn14
mel_bins: 80
emb_dim: 2048
norm_type: bn
classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
input_size: 2048
out_neurons: !ref <out_n_neurons>
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
|