EBranchformer_SV

README.md

@@ -1,3 +1,19 @@
 ---
 license: cc-by-4.0
 ---
+# RESULTS
+## Environments
+date: 2024-11-11 13:27:22.449116
+
+- python version: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
+- espnet version: 202409
+- pytorch version: 2.2.2+rocm5.6
+
+| | Mean | Std |
+|---|---|---|
+| Target | 8.1720 | 3.9750 |
+| Non-target | 2.0805 | 2.0805 |
+
+| Model name | EER(%) | minDCF |
+|---|---|---|
+| conf/tuning/train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop | 0.638 | 0.04797 |

spk_train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop_raw/40epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6772cffb1283459b3d342411022b30ec7d32ded12f15855c8ba89b2c976eac2c
+size 156441550

spk_train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop_raw/RESULTS.md

@@ -0,0 +1,17 @@
+<!-- Generated by scripts/utils/show_spk_result.py -->
+# RESULTS
+## Environments
+date: 2024-11-11 13:27:22.449116
+
+- python version: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]
+- espnet version: 202409
+- pytorch version: 2.2.2+rocm5.6
+
+| | Mean | Std |
+|---|---|---|
+| Target | 8.1720 | 3.9750 |
+| Non-target | 2.0805 | 2.0805 |
+
+| Model name | EER(%) | minDCF |
+|---|---|---|
+| conf/tuning/train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop | 0.638 | 0.04797 |

spk_train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop_raw/config.yaml

@@ -0,0 +1,226 @@
+config: conf/tuning/train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop.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_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop_raw
+ngpu: 1
+seed: 0
+num_workers: 6
+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: null
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+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: false
+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: 200
+valid_batch_size: 80
+batch_bins: 1000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/spk_stats_16k/train/speech_shape
+valid_shape_file:
+- exp/spk_stats_16k/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/voxceleb12_devs/wav.scp
+    - speech
+    - sound
+-   - dump/raw/voxceleb12_devs/utt2spk
+    - spk_labels
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/voxceleb1_test/trial.scp
+    - speech
+    - sound
+-   - dump/raw/voxceleb1_test/trial2.scp
+    - speech2
+    - sound
+-   - dump/raw/voxceleb1_test/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: adamw
+optim_conf:
+    lr: 0.001
+    weight_decay: 0.0001
+    amsgrad: false
+scheduler: cosineannealingwarmuprestarts
+scheduler_conf:
+    first_cycle_steps: 300000
+    cycle_mult: 1.0
+    max_lr: 0.001
+    min_lr: 1.0e-07
+    warmup_steps: 30000
+    gamma: 0.7
+init: null
+use_preprocessor: true
+input_size: null
+target_duration: 3.0
+spk2utt: dump/raw/voxceleb12_devs/spk2utt
+spk_num: 7205
+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: e_branchformer
+encoder_conf:
+    output_size: 384
+    attention_heads: 6
+    attention_layer_type: rel_selfattn
+    pos_enc_layer_type: rel_pos
+    rel_pos_type: latest
+    cgmlp_linear_units: 1536
+    cgmlp_conv_kernel: 31
+    use_linear_after_conv: false
+    gate_activation: identity
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d2
+    layer_drop_rate: 0.05
+    linear_units: 1536
+    positionwise_layer_type: linear
+    use_ffn: true
+    macaron_ffn: true
+    merge_conv_kernel: 31
+    aggregate_layer: true
+pooling: chn_attn_stat
+pooling_conf: {}
+projector: rawnet3
+projector_conf:
+    output_size: 192
+preprocessor: spk
+preprocessor_conf:
+    target_duration: 3.0
+    sample_rate: 16000
+    num_eval: 5
+    noise_apply_prob: 0.6
+    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
+        -   - 0
+            - 15
+    rir_apply_prob: 0.6
+    rir_scp: dump/raw/rirs.scp
+loss: aamsoftmax_sc_topk
+loss_conf:
+    margin: 0.2
+    scale: 32
+    K: 3
+    mp: 0.06
+    k_top: 5
+required:
+- output_dir
+version: '202409'
+distributed: true

spk_train_ebranchformer_aggregate_sys1_D384_L6_Rel_LayerDrop_raw/latest.pth

@@ -0,0 +1 @@
+40epoch.pth