English
Sound Classification
CNN14
cnn14-esc50 / hyperparams.yaml
cemsubakan's picture
Update hyperparams.yaml
422a112 verified
raw
history blame
1.86 kB
# CNN14 inference
sample_rate: 44100
# Feature parameters
n_mels: 80
left_frames: 0
right_frames: 0
deltas: false
amp_to_db: true
normalize: true
use_melspectra: true
# Number of classes
out_n_neurons: 50
device: cpu
# Functions
compute_features: !new:speechbrain.lobes.features.Fbank
n_mels: 80
left_frames: 0
right_frames: 0
deltas: false
sample_rate: 44100
n_fft: 1024
win_length: 20
hop_length: 10
use_pretrain: false
embedding_model: !new:speechbrain.lobes.models.Cnn14.Cnn14
mel_bins: 80
emb_dim: 2048
classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
input_size: 2048
out_neurons: 50
lin_blocks: 1
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
norm_type: sentence
std_norm: false
# pre-processing
n_fft: 1024
spec_mag_power: 0.5
hop_length: 11.6099
win_length: 23.2199
compute_stft: !new:speechbrain.processing.features.STFT
n_fft: 1024
hop_length: 11.6099
win_length: 23.2199
sample_rate: 44100
compute_fbank: !new:speechbrain.processing.features.Filterbank
n_mels: 80
n_fft: 1024
sample_rate: 44100
modules:
compute_stft: !ref <compute_stft>
compute_fbank: !ref <compute_fbank>
compute_features: !ref <compute_features>
embedding_model: !ref <embedding_model>
classifier: !ref <classifier>
mean_var_norm: !ref <mean_var_norm>
label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
pretrained_path: speechbrain/cnn14-esc50
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_esc50ft.ckpt
classifier: !ref <pretrained_path>/classifier_esc50.ckpt
label_encoder: !ref <pretrained_path>/label_encoder.txt