File size: 1,959 Bytes
09e18b1 37b3478 09e18b1 78e0d8f 09e18b1 78e0d8f 09e18b1 78e0d8f 09e18b1 |
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 59 60 61 62 63 64 65 |
# ############################################################################
# Model: ECAPA-TDNN for Audio Classification
# ############################################################################
# Pretrain folder (HuggingFace)
pretrained_path: dragonSwing/audify
# Feature parameters
n_mels: 80
# Output parameters
out_n_neurons: 5 # Possible languages in the dataset
# Model params
compute_features: !new:speechbrain.lobes.features.Fbank
n_mels: !ref <n_mels>
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
norm_type: sentence
std_norm: False
# Embedding Model
CNN: !new:speechbrain.lobes.models.convolution.ConvolutionFrontEnd
input_shape: (null, null, 80)
num_blocks: 3
num_layers_per_block: 1
out_channels: (128, 256, 256)
kernel_sizes: (3, 3, 1)
strides: (2, 2, 1)
residuals: (False, False, False)
conv_module: !name:speechbrain.nnet.CNN.Conv1d
norm: !name:speechbrain.nnet.normalization.BatchNorm1d
pooling: !new:speechbrain.nnet.pooling.AdaptivePool
output_size: 1
embedding: !new:torch.nn.ModuleList
- [!ref <CNN>, !ref <pooling>]
embedding_model: !new:speechbrain.nnet.containers.LengthsCapableSequential
CNN: !ref <CNN>
pooling: !ref <pooling>
classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
input_size: 256
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>
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
|