|
config: conf/train_resnet221.yaml |
|
print_config: false |
|
log_level: INFO |
|
drop_last_iter: true |
|
dry_run: false |
|
iterator_type: category |
|
valid_iterator_type: sequence |
|
output_dir: exp/spk_train_resnet221_raw_sp |
|
ngpu: 1 |
|
seed: 0 |
|
num_workers: 8 |
|
num_att_plot: 0 |
|
dist_backend: nccl |
|
dist_init_method: env:// |
|
dist_world_size: 8 |
|
dist_rank: 0 |
|
local_rank: 0 |
|
dist_master_addr: localhost |
|
dist_master_port: 42677 |
|
dist_launcher: null |
|
multiprocessing_distributed: true |
|
unused_parameters: false |
|
sharded_ddp: false |
|
use_deepspeed: false |
|
deepspeed_config: null |
|
gradient_as_bucket_view: true |
|
ddp_comm_hook: null |
|
cudnn_enabled: true |
|
cudnn_benchmark: true |
|
cudnn_deterministic: false |
|
use_tf32: false |
|
collect_stats: false |
|
write_collected_feats: false |
|
max_epoch: 40 |
|
patience: null |
|
val_scheduler_criterion: |
|
- valid |
|
- loss |
|
early_stopping_criterion: |
|
- valid |
|
- loss |
|
- min |
|
best_model_criterion: |
|
- - valid |
|
- eer |
|
- min |
|
keep_nbest_models: 3 |
|
nbest_averaging_interval: 0 |
|
grad_clip: 9999 |
|
grad_clip_type: 2.0 |
|
grad_noise: false |
|
accum_grad: 1 |
|
no_forward_run: false |
|
resume: true |
|
train_dtype: float32 |
|
use_amp: true |
|
log_interval: 100 |
|
use_matplotlib: true |
|
use_tensorboard: true |
|
create_graph_in_tensorboard: false |
|
use_wandb: false |
|
wandb_project: null |
|
wandb_id: null |
|
wandb_entity: null |
|
wandb_name: null |
|
wandb_model_log_interval: -1 |
|
detect_anomaly: false |
|
use_adapter: false |
|
adapter: lora |
|
save_strategy: all |
|
adapter_conf: {} |
|
pretrain_path: null |
|
init_param: [] |
|
ignore_init_mismatch: false |
|
freeze_param: [] |
|
num_iters_per_epoch: null |
|
batch_size: 256 |
|
valid_batch_size: 40 |
|
batch_bins: 1000000 |
|
valid_batch_bins: null |
|
category_sample_size: 10 |
|
train_shape_file: |
|
- exp/spk_stats_16k_sp/train/speech_shape |
|
valid_shape_file: |
|
- exp/spk_stats_16k_sp/valid/speech_shape |
|
batch_type: folded |
|
valid_batch_type: null |
|
fold_length: |
|
- 120000 |
|
sort_in_batch: descending |
|
shuffle_within_batch: false |
|
sort_batch: descending |
|
multiple_iterator: false |
|
chunk_length: 500 |
|
chunk_shift_ratio: 0.5 |
|
num_cache_chunks: 1024 |
|
chunk_excluded_key_prefixes: [] |
|
chunk_default_fs: null |
|
chunk_max_abs_length: null |
|
chunk_discard_short_samples: true |
|
train_data_path_and_name_and_type: |
|
- - dump/raw/cnceleb_train_sp/wav.scp |
|
- speech |
|
- sound |
|
- - dump/raw/cnceleb_train_sp/utt2spk |
|
- spk_labels |
|
- text |
|
valid_data_path_and_name_and_type: |
|
- - dump/raw/cnceleb1_valid/trial.scp |
|
- speech |
|
- sound |
|
- - dump/raw/cnceleb1_valid/trial2.scp |
|
- speech2 |
|
- sound |
|
- - dump/raw/cnceleb1_valid/trial_label |
|
- spk_labels |
|
- text |
|
multi_task_dataset: false |
|
allow_variable_data_keys: false |
|
max_cache_size: 0.0 |
|
max_cache_fd: 32 |
|
allow_multi_rates: false |
|
valid_max_cache_size: null |
|
exclude_weight_decay: false |
|
exclude_weight_decay_conf: {} |
|
optim: sgd |
|
optim_conf: |
|
lr: 0.1 |
|
momentum: 0.9 |
|
weight_decay: 0.0001 |
|
scheduler: exponentialdecaywarmup |
|
scheduler_conf: |
|
max_lr: 0.1 |
|
min_lr: 5.0e-05 |
|
total_steps: 290720 |
|
warmup_steps: 36340 |
|
warm_from_zero: true |
|
init: null |
|
use_preprocessor: true |
|
input_size: null |
|
target_duration: 3.0 |
|
spk2utt: dump/raw/cnceleb_train_sp/spk2utt |
|
spk_num: 8379 |
|
sample_rate: 16000 |
|
num_eval: 10 |
|
rir_scp: '' |
|
model_conf: |
|
extract_feats_in_collect_stats: false |
|
frontend: melspec_torch |
|
frontend_conf: |
|
preemp: true |
|
n_fft: 512 |
|
log: true |
|
win_length: 400 |
|
hop_length: 160 |
|
n_mels: 80 |
|
normalize: mn |
|
specaug: null |
|
specaug_conf: {} |
|
normalize: null |
|
normalize_conf: {} |
|
encoder: resnet |
|
encoder_conf: |
|
resnet_type: resnet221 |
|
pooling: stats |
|
pooling_conf: {} |
|
projector: rawnet3 |
|
projector_conf: |
|
output_size: 256 |
|
preprocessor: spk |
|
preprocessor_conf: |
|
target_duration: 3.0 |
|
sample_rate: 16000 |
|
num_eval: 5 |
|
noise_apply_prob: 0.5 |
|
noise_info: |
|
- - 1.0 |
|
- dump/raw/musan_speech.scp |
|
- - 4 |
|
- 7 |
|
- - 13 |
|
- 20 |
|
- - 1.0 |
|
- dump/raw/musan_noise.scp |
|
- - 1 |
|
- 1 |
|
- - 0 |
|
- 15 |
|
- - 1.0 |
|
- dump/raw/musan_music.scp |
|
- - 1 |
|
- 1 |
|
- - 5 |
|
- 15 |
|
rir_apply_prob: 0.5 |
|
rir_scp: dump/raw/rirs.scp |
|
loss: aamsoftmax_sc_topk |
|
loss_conf: |
|
margin: 0.3 |
|
scale: 30 |
|
K: 3 |
|
mp: 0.06 |
|
k_top: 5 |
|
required: |
|
- output_dir |
|
version: '202402' |
|
distributed: true |
|
|