google_speech_command_xvector / hyperparams.yaml
Mirco's picture
upload model
14e4238
# ############################################################################
# Model: xvector for Command Recognition with Google Speech Commands
# ############################################################################
# Pretrain folder (HuggingFace)
pretrained_path: speechbrain/google_speech_command_xvector
# Feature parameters
n_mels: 24
# Output parameters
out_n_neurons: 12 # 12 command version
# 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: !new:speechbrain.lobes.models.Xvector.Xvector
in_channels: !ref <n_mels>
activation: !name:torch.nn.LeakyReLU
tdnn_blocks: 5
tdnn_channels: [512, 512, 512, 512, 1500]
tdnn_kernel_sizes: [5, 3, 3, 1, 1]
tdnn_dilations: [1, 2, 3, 1, 1]
lin_neurons: 512
classifier: !new:speechbrain.lobes.models.Xvector.Classifier
input_shape: [null, null, 512]
activation: !name:torch.nn.LeakyReLU
lin_blocks: 1
lin_neurons: 512
out_neurons: !ref <out_n_neurons>
mean_var_norm_emb: !new:speechbrain.processing.features.InputNormalization
norm_type: global
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