Update model

README.md

@@ -11,7 +11,7 @@ license: cc-by-4.0
 
 ## ESPnet2 SPK model
 
-### `espnet/voxcelebs12_ecapa`
+### `espnet/voxcelebs12_ecapa_wavlm_joint`
 
 This model was trained by Jungjee using voxceleb recipe in [espnet](https://github.com/espnet/espnet/).
 
@@ -22,16 +22,16 @@ if you haven't done that already.
 
 ```bash
 cd espnet
-git checkout 53b99bf9bc043c4444b760f1d53ab719c77cb386
+git checkout e5da124138fc58708fcdda03fd8d4e02fe5d7c65
 pip install -e .
 cd egs2/voxceleb/spk1
-./run.sh --skip_data_prep false --skip_train true --download_model espnet/voxcelebs12_ecapa
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/voxcelebs12_ecapa_wavlm_joint
 ```
 
 <!-- Generated by scripts/utils/show_spk_result.py -->
 # RESULTS
 ## Environments
-date: 2023-11-30 15:56:55.514299
+date: 2023-12-05 12:47:46.810012
 
 - python version: 3.9.16 (main, Mar  8 2023, 14:00:05)  [GCC 11.2.0]
 - espnet version: 202310
@@ -39,26 +39,26 @@ date: 2023-11-30 15:56:55.514299
 
 | | Mean | Std |
 |---|---|---|
-| Target | -0.7353 | 0.1212 |
-| Non-target | 0.0916 | 0.0916 |
+| Target | -0.7332 | 0.1202 |
+| Non-target | 0.0910 | 0.0910 |
 
 | Model name | EER(%) | minDCF |
 |---|---|---|
-| ecapa_wavlm_joint | 0.425 | 0.04015 |
+| conf/tuning/train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11 | 0.415 | 0.03813 |
 
 ## SPK config
 
 <details><summary>expand</summary>
 
 ```
-config: conf/tuning/train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt9.yaml
+config: conf/tuning/train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11.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_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt9_raw_sp
+output_dir: exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp
 ngpu: 1
 seed: 0
 num_workers: 8
@@ -69,7 +69,7 @@ dist_world_size: 4
 dist_rank: 0
 local_rank: 0
 dist_master_addr: localhost
-dist_master_port: 38103
+dist_master_port: 57359
 dist_launcher: null
 multiprocessing_distributed: true
 unused_parameters: true
@@ -92,7 +92,7 @@ best_model_criterion:
 -   - valid
     - eer
     - min
-keep_nbest_models: 3
+keep_nbest_models: 2
 nbest_averaging_interval: 0
 grad_clip: 9999
 grad_clip_type: 2.0
@@ -121,7 +121,7 @@ init_param:
 - save_exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_raw_sp/valid.eer.best.pth
 ignore_init_mismatch: false
 freeze_param: []
-num_iters_per_epoch: 16000
+num_iters_per_epoch: 8000
 batch_size: 64
 valid_batch_size: 5
 batch_bins: 1000000
@@ -174,11 +174,11 @@ optim_conf:
     amsgrad: false
 scheduler: cosineannealingwarmuprestarts
 scheduler_conf:
-    first_cycle_steps: 320000
+    first_cycle_steps: 10000
     cycle_mult: 1.0
-    max_lr: 0.0001
+    max_lr: 5.0e-05
     min_lr: 5.0e-06
-    warmup_steps: 2000
+    warmup_steps: 1000
     gamma: 0.75
 init: null
 use_preprocessor: true

exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp/8epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c364606a99dd5f2de03caaf936388d0a437fbd41262828f741cadec600372ab8
+size 1389974254

exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp/RESULTS.md

@@ -0,0 +1,17 @@
+<!-- Generated by scripts/utils/show_spk_result.py -->
+# RESULTS
+## Environments
+date: 2023-12-05 12:47:46.810012
+
+- python version: 3.9.16 (main, Mar  8 2023, 14:00:05)  [GCC 11.2.0]
+- espnet version: 202310
+- pytorch version: 2.0.1
+
+| | Mean | Std |
+|---|---|---|
+| Target | -0.7332 | 0.1202 |
+| Non-target | 0.0910 | 0.0910 |
+
+| Model name | EER(%) | minDCF |
+|---|---|---|
+| conf/tuning/train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11 | 0.415 | 0.03813 |

exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp/config.yaml

@@ -0,0 +1,199 @@
+config: conf/tuning/train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11.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_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp
+ngpu: 1
+seed: 0
+num_workers: 8
+num_att_plot: 0
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 4
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 57359
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: true
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: true
+cudnn_deterministic: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 20
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - eer
+    - min
+keep_nbest_models: 2
+nbest_averaging_interval: 0
+grad_clip: 9999
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 16
+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_lora: false
+save_lora_only: true
+lora_conf: {}
+pretrain_path: null
+init_param:
+- save_exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_raw_sp/valid.eer.best.pth
+ignore_init_mismatch: false
+freeze_param: []
+num_iters_per_epoch: 8000
+batch_size: 64
+valid_batch_size: 5
+batch_bins: 1000000
+valid_batch_bins: null
+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
+train_data_path_and_name_and_type:
+-   - dump/raw/voxceleb12_devs_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/voxceleb12_devs_sp/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
+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: 0.0001
+    weight_decay: 1.0e-05
+    amsgrad: false
+scheduler: cosineannealingwarmuprestarts
+scheduler_conf:
+    first_cycle_steps: 10000
+    cycle_mult: 1.0
+    max_lr: 5.0e-05
+    min_lr: 5.0e-06
+    warmup_steps: 1000
+    gamma: 0.75
+init: null
+use_preprocessor: true
+input_size: null
+target_duration: 3.0
+spk2utt: dump/raw/voxceleb12_devs_sp/spk2utt
+spk_num: 21615
+sample_rate: 16000
+num_eval: 10
+rir_scp: ''
+model_conf:
+    extract_feats_in_collect_stats: false
+frontend: s3prl
+frontend_conf:
+    frontend_conf:
+        upstream: wavlm_large
+    download_dir: ./hub
+    multilayer_feature: true
+specaug: null
+specaug_conf: {}
+normalize: utterance_mvn
+normalize_conf:
+    norm_vars: false
+encoder: ecapa_tdnn
+encoder_conf:
+    model_scale: 8
+    ndim: 1024
+    output_size: 1536
+pooling: chn_attn_stat
+pooling_conf: {}
+projector: rawnet3
+projector_conf:
+    output_size: 192
+preprocessor: spk
+preprocessor_conf:
+    target_duration: 6.0
+    sample_rate: 16000
+    num_eval: 3
+    noise_apply_prob: 0.0
+    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: 0.0
+    rir_scp: dump/raw/rirs.scp
+loss: aamsoftmax_sc_topk
+loss_conf:
+    margin: 0.5
+    scale: 30
+    K: 3
+    mp: 0.06
+    k_top: 5
+required:
+- output_dir
+version: '202310'
+distributed: true

meta.yaml

@@ -1,8 +1,8 @@
 espnet: '202310'
 files:
-  model_file: exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt9_raw_sp/3epoch.pth
+  model_file: exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp/8epoch.pth
 python: "3.9.16 (main, Mar  8 2023, 14:00:05) \n[GCC 11.2.0]"
-timestamp: 1701378221.436117
+timestamp: 1704236578.76806
 torch: 2.0.1
 yaml_files:
-  train_config: exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt9_raw_sp/config.yaml
+  train_config: exp/spk_train_ecapa_Vox12_emb192_torchmelspec_subcentertopk_wavlm_jt11_raw_sp/config.yaml