|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
seed: 651 |
|
__set_seed: !apply:torch.manual_seed [651] |
|
output_folder: /media/wakeb/T7 Touch/speechbrain651 |
|
save_folder: /media/wakeb/T7 Touch/speechbrain651/save |
|
train_log: /media/wakeb/T7 Touch/speechbrain651/train_log.txt |
|
|
|
|
|
data_folder: /media/wakeb/T7 Touch/data_qasr/ |
|
train_annotation: /media/wakeb/T7 Touch/data_qasr/train_reworked.csv |
|
valid_annotation: /media/wakeb/T7 Touch/data_qasr/dev_reworked.csv |
|
|
|
|
|
rir_folder: /media/wakeb/T7 Touch/data_qasr/ |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
verification_file: /media/wakeb/T7 Touch/data_qasr/testing.txt |
|
|
|
split_ratio: [90, 10] |
|
skip_prep: true |
|
ckpt_interval_minutes: 15 |
|
|
|
|
|
number_of_epochs: 30 |
|
batch_size: 140 |
|
lr: 0.001 |
|
lr_final: 0.000001 |
|
|
|
sample_rate: 16000 |
|
sentence_len: 3 |
|
shuffle: false |
|
random_chunk: true |
|
|
|
|
|
n_mels: 24 |
|
left_frames: 0 |
|
right_frames: 0 |
|
deltas: false |
|
|
|
|
|
out_n_neurons: 2917 |
|
emb_dim: 512 |
|
|
|
dataloader_options: |
|
batch_size: 140 |
|
shuffle: false |
|
num_workers: 0 |
|
|
|
|
|
compute_features: &id006 !new:speechbrain.lobes.features.Fbank |
|
n_mels: 24 |
|
left_frames: 0 |
|
right_frames: 0 |
|
deltas: false |
|
|
|
embedding_model: &id007 !new:speechbrain.lobes.models.Xvector.Xvector |
|
in_channels: 24 |
|
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: &id008 !new:speechbrain.lobes.models.Xvector.Classifier |
|
input_shape: [null, null, 512] |
|
activation: !name:torch.nn.LeakyReLU |
|
lin_blocks: 1 |
|
lin_neurons: 512 |
|
out_neurons: 2917 |
|
|
|
epoch_counter: &id010 !new:speechbrain.utils.epoch_loop.EpochCounter |
|
limit: 30 |
|
|
|
|
|
augment_wavedrop: &id001 !new:speechbrain.lobes.augment.TimeDomainSpecAugment |
|
sample_rate: 16000 |
|
speeds: [100] |
|
|
|
augment_speed: &id002 !new:speechbrain.lobes.augment.TimeDomainSpecAugment |
|
sample_rate: 16000 |
|
speeds: [95, 100, 105] |
|
|
|
add_rev: &id003 !new:speechbrain.lobes.augment.EnvCorrupt |
|
openrir_folder: /media/wakeb/T7 Touch/data_qasr/ |
|
openrir_max_noise_len: 3.0 |
|
reverb_prob: 1.0 |
|
noise_prob: 0.0 |
|
noise_snr_low: 0 |
|
noise_snr_high: 15 |
|
rir_scale_factor: 1.0 |
|
|
|
add_noise: &id004 !new:speechbrain.lobes.augment.EnvCorrupt |
|
openrir_folder: /media/wakeb/T7 Touch/data_qasr/ |
|
openrir_max_noise_len: 3.0 |
|
reverb_prob: 0.0 |
|
noise_prob: 1.0 |
|
noise_snr_low: 0 |
|
noise_snr_high: 15 |
|
rir_scale_factor: 1.0 |
|
|
|
add_rev_noise: &id005 !new:speechbrain.lobes.augment.EnvCorrupt |
|
openrir_folder: /media/wakeb/T7 Touch/data_qasr/ |
|
openrir_max_noise_len: 3.0 |
|
reverb_prob: 1.0 |
|
noise_prob: 1.0 |
|
noise_snr_low: 0 |
|
noise_snr_high: 15 |
|
rir_scale_factor: 1.0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
augment_pipeline: [*id001, *id002, *id003, *id004, *id005] |
|
concat_augment: true |
|
|
|
mean_var_norm: &id009 !new:speechbrain.processing.features.InputNormalization |
|
|
|
|
|
norm_type: sentence |
|
std_norm: false |
|
|
|
modules: |
|
compute_features: *id006 |
|
augment_wavedrop: *id001 |
|
augment_speed: *id002 |
|
add_rev: *id003 |
|
add_noise: *id004 |
|
add_rev_noise: *id005 |
|
embedding_model: *id007 |
|
classifier: *id008 |
|
mean_var_norm: *id009 |
|
compute_cost: !name:speechbrain.nnet.losses.nll_loss |
|
|
|
|
|
opt_class: !name:torch.optim.Adam |
|
lr: 0.001 |
|
weight_decay: 0.000002 |
|
|
|
lr_annealing: !new:speechbrain.nnet.schedulers.LinearScheduler |
|
initial_value: 0.001 |
|
final_value: 0.000001 |
|
epoch_count: 30 |
|
|
|
|
|
train_logger: !new:speechbrain.utils.train_logger.FileTrainLogger |
|
save_file: /media/wakeb/T7 Touch/speechbrain651/train_log.txt |
|
|
|
error_stats: !name:speechbrain.utils.metric_stats.MetricStats |
|
metric: !name:speechbrain.nnet.losses.classification_error |
|
reduction: batch |
|
|
|
checkpointer: !new:speechbrain.utils.checkpoints.Checkpointer |
|
checkpoints_dir: /media/wakeb/T7 Touch/speechbrain651/save |
|
recoverables: |
|
embedding_model: *id007 |
|
classifier: *id008 |
|
normalizer: *id009 |
|
counter: *id010 |
|
|