File size: 1,708 Bytes
7f5fd22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9a27c7
7f5fd22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# ############################################################################
# Model: ECAPA small for Speaker verification
# Authors: Yang Wang
# ############################################################################

# Feature parameters
n_mels: 80
deltas: False

# Pretrain folder (HuggingFace)
pretrained_path: yangwang825/ecapa-tdnn-vox2

# Output parameters
out_n_neurons: 5994

# Model params
compute_features: !new:speechbrain.lobes.features.Fbank
    n_mels: !ref <n_mels>
    deltas: !ref <deltas>

mean_var_norm: !new:speechbrain.processing.features.InputNormalization
    norm_type: sentence
    std_norm: False

embedding_model: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
    input_size: !ref <n_mels>
    channels: [512, 512, 512, 512, 1536]
    kernel_sizes: [5, 3, 3, 3, 1]
    dilations: [1, 2, 3, 4, 1]
    groups: [1, 1, 1, 1, 1]
    attention_channels: 128
    lin_neurons: 192

classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
    input_size: 192
    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