| config: ./conf/tuning/train_enh_tfgridnet.yaml |
| print_config: false |
| log_level: INFO |
| drop_last_iter: false |
| dry_run: false |
| iterator_type: chunk |
| valid_iterator_type: null |
| output_dir: exp/enh_train_enh_tfgridnet_raw |
| ngpu: 1 |
| seed: 0 |
| num_workers: 8 |
| num_att_plot: 3 |
| dist_backend: nccl |
| dist_init_method: env:// |
| dist_world_size: 2 |
| dist_rank: 0 |
| local_rank: 0 |
| dist_master_addr: localhost |
| dist_master_port: 53661 |
| 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: false |
| cudnn_deterministic: true |
| use_tf32: false |
| collect_stats: false |
| write_collected_feats: false |
| max_epoch: 35 |
| patience: 5 |
| val_scheduler_criterion: |
| - valid |
| - loss |
| early_stopping_criterion: |
| - valid |
| - loss |
| - min |
| best_model_criterion: |
| - - valid |
| - si_snr |
| - max |
| - - valid |
| - loss |
| - min |
| keep_nbest_models: 5 |
| nbest_averaging_interval: 0 |
| grad_clip: 5.0 |
| grad_clip_type: 2.0 |
| grad_noise: false |
| accum_grad: 1 |
| no_forward_run: false |
| resume: true |
| train_dtype: float32 |
| use_amp: false |
| log_interval: null |
| 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: 5000 |
| batch_size: 4 |
| valid_batch_size: null |
| batch_bins: 1000000 |
| valid_batch_bins: null |
| category_sample_size: 10 |
| upsampling_factor: 0.5 |
| category_upsampling_factor: 0.5 |
| dataset_upsampling_factor: 0.5 |
| dataset_scaling_factor: 1.2 |
| max_batch_size: null |
| min_batch_size: 1 |
| train_shape_file: |
| - exp/enh_stats_16k/train/speech_mix_shape |
| - exp/enh_stats_16k/train/speech_ref1_shape |
| - exp/enh_stats_16k/train/noise_ref1_shape |
| valid_shape_file: |
| - exp/enh_stats_16k/valid/speech_mix_shape |
| - exp/enh_stats_16k/valid/speech_ref1_shape |
| - exp/enh_stats_16k/valid/noise_ref1_shape |
| batch_type: folded |
| valid_batch_type: null |
| fold_length: |
| - 80000 |
| - 80000 |
| - 80000 |
| sort_in_batch: descending |
| shuffle_within_batch: false |
| sort_batch: descending |
| multiple_iterator: false |
| chunk_length: 48000 |
| 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/tr_ms_snsd/wav.scp |
| - speech_mix |
| - sound |
| - - dump/raw/tr_ms_snsd/spk1.scp |
| - speech_ref1 |
| - sound |
| - - dump/raw/tr_ms_snsd/noise1.scp |
| - noise_ref1 |
| - sound |
| valid_data_path_and_name_and_type: |
| - - dump/raw/cv_ms_snsd/wav.scp |
| - speech_mix |
| - sound |
| - - dump/raw/cv_ms_snsd/spk1.scp |
| - speech_ref1 |
| - sound |
| - - dump/raw/cv_ms_snsd/noise1.scp |
| - noise_ref1 |
| - sound |
| 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: adam |
| optim_conf: |
| lr: 0.001 |
| eps: 1.0e-08 |
| weight_decay: 0 |
| scheduler: reducelronplateau |
| scheduler_conf: |
| mode: min |
| factor: 0.7 |
| patience: 1 |
| init: xavier_uniform |
| model_conf: |
| stft_consistency: false |
| loss_type: mask_mse |
| mask_type: null |
| flexible_numspk: false |
| extract_feats_in_collect_stats: false |
| normalize_variance: false |
| normalize_variance_per_ch: false |
| categories: [] |
| category_weights: [] |
| always_forward_in_48k: false |
| criterions: |
| - name: mr_l1_tfd |
| conf: |
| window_sz: |
| - 256 |
| - 512 |
| - 768 |
| - 1024 |
| hop_sz: null |
| eps: 1.0e-08 |
| time_domain_weight: 0.5 |
| wrapper: fixed_order |
| wrapper_conf: |
| weight: 1.0 |
| - name: si_snr |
| conf: |
| eps: 1.0e-07 |
| wrapper: fixed_order |
| wrapper_conf: |
| weight: 0.0 |
| speech_volume_normalize: null |
| rir_scp: null |
| rir_apply_prob: 1.0 |
| noise_scp: null |
| noise_apply_prob: 1.0 |
| noise_db_range: '13_15' |
| short_noise_thres: 0.5 |
| use_reverberant_ref: false |
| num_spk: 1 |
| num_noise_type: 1 |
| sample_rate: 8000 |
| force_single_channel: false |
| channel_reordering: false |
| categories: [] |
| speech_segment: null |
| avoid_allzero_segment: true |
| flexible_numspk: false |
| dynamic_mixing: false |
| utt2spk: null |
| dynamic_mixing_gain_db: 0.0 |
| encoder: same |
| encoder_conf: {} |
| separator: tfgridnet |
| separator_conf: |
| n_srcs: 1 |
| n_fft: 512 |
| stride: 256 |
| window: hann |
| n_imics: 1 |
| n_layers: 4 |
| lstm_hidden_units: 128 |
| attn_n_head: 4 |
| attn_approx_qk_dim: 512 |
| emb_dim: 32 |
| emb_ks: 4 |
| emb_hs: 4 |
| activation: prelu |
| eps: 1.0e-05 |
| decoder: same |
| decoder_conf: {} |
| mask_module: multi_mask |
| mask_module_conf: {} |
| preprocessor: null |
| preprocessor_conf: {} |
| diffusion_model: null |
| diffusion_model_conf: {} |
| required: |
| - output_dir |
| version: '202511' |
| distributed: true |
|
|
