File size: 4,657 Bytes
db346ec |
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 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
name: &name "TitaNet-Finetune"
sample_rate: &sample_rate 16000
init_from_pretrained_model:
speaker_tasks:
name: 'titanet_large'
include: ["preprocessor","encoder"]
exclude: ["decoder.final"] # Add specific layer names here to exlude or just ["decoder"] if to exclude all of decoder pretrained weights
model:
train_ds:
manifest_filepath: ???
sample_rate: 16000
labels: null
batch_size: 64
shuffle: True
is_tarred: False
tarred_audio_filepaths: null
tarred_shard_strategy: "scatter"
augmentor:
speed:
prob: 0.3
sr: *sample_rate
resample_type: 'kaiser_fast'
min_speed_rate: 0.95
max_speed_rate: 1.05
validation_ds:
manifest_filepath: ???
sample_rate: 16000
labels: null
batch_size: 128
shuffle: False
test_ds:
manifest_filepath: ???
sample_rate: 16000
labels: null
batch_size: 1
shuffle: False
embedding_dir: './embeddings'
model_defaults:
filters: 1024
repeat: 3
dropout: 0.1
separable: true
se: true
se_context_size: -1
kernel_size_factor: 1.0
preprocessor:
_target_: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor
normalize: "per_feature"
window_size: 0.025
sample_rate: *sample_rate
window_stride: 0.01
window: "hann"
features: &n_mels 80
n_fft: 512
frame_splicing: 1
dither: 0.00001
encoder:
_target_: nemo.collections.asr.modules.ConvASREncoder
feat_in: *n_mels
activation: relu
conv_mask: true
jasper:
- filters: ${model.model_defaults.filters}
repeat: 1
kernel: [3]
stride: [1]
dilation: [1]
dropout: 0.0
residual: false
separable: ${model.model_defaults.separable}
se: ${model.model_defaults.se}
se_context_size: ${model.model_defaults.se_context_size}
- filters: ${model.model_defaults.filters}
repeat: ${model.model_defaults.repeat}
kernel: [7]
stride: [1]
dilation: [1]
dropout: ${model.model_defaults.dropout}
residual: true
separable: ${model.model_defaults.separable}
se: ${model.model_defaults.se}
se_context_size: ${model.model_defaults.se_context_size}
- filters: ${model.model_defaults.filters}
repeat: ${model.model_defaults.repeat}
kernel: [11]
stride: [1]
dilation: [1]
dropout: ${model.model_defaults.dropout}
residual: true
separable: ${model.model_defaults.separable}
se: ${model.model_defaults.se}
se_context_size: ${model.model_defaults.se_context_size}
- filters: ${model.model_defaults.filters}
repeat: ${model.model_defaults.repeat}
kernel: [15]
stride: [1]
dilation: [1]
dropout: ${model.model_defaults.dropout}
residual: true
separable: ${model.model_defaults.separable}
se: ${model.model_defaults.se}
se_context_size: ${model.model_defaults.se_context_size}
- filters: &enc_feat_out 3072
repeat: 1
kernel: [1]
stride: [1]
dilation: [1]
dropout: 0.0
residual: false
separable: ${model.model_defaults.separable}
se: ${model.model_defaults.se}
se_context_size: ${model.model_defaults.se_context_size}
decoder:
_target_: nemo.collections.asr.modules.SpeakerDecoder
feat_in: *enc_feat_out
num_classes: ???
pool_mode: 'attention'
emb_sizes: 192
loss:
_target_: nemo.collections.asr.losses.angularloss.AngularSoftmaxLoss # you could also use cross-entrophy loss
scale: 30
margin: 0.2
optim_param_groups:
encoder:
lr: .001
optim:
name: adamw
lr: .0001 #(original titanet-large was trained with 0.08 lr)
weight_decay: 0.0002
# scheduler setup
sched:
name: CosineAnnealing
warmup_ratio: 0.1
min_lr: 0.0
trainer:
devices: 1 # number of gpus (original titanet-large was trained on 4 nodes with 8 gpus each)
max_epochs: 10
max_steps: -1 # computed at runtime if not set
num_nodes: 1
accelerator: gpu
strategy: ddp
deterministic: True
enable_checkpointing: False
logger: False
log_every_n_steps: 1 # Interval of logging.
val_check_interval: 1.0 # Set to 0.25 to check 4 times per epoch, or an int for number of iterations
gradient_clip_val: 1.0
exp_manager:
exp_dir: null
name: *name
create_tensorboard_logger: True
create_checkpoint_callback: True
|