Update model

README.md

@@ -1,3 +1,275 @@
----
-license: cc-by-4.0
----
+---
+tags:
+- espnet
+- audio
+- speaker-recognition
+language: multilingual
+datasets:
+- TEMPLATE
+license: cc-by-4.0
+---
+
+## ESPnet2 SPK model
+
+### `espnet/rats_ska_wavlm_frozen`
+
+This model was trained by shimhz using TEMPLATE recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Demo: How to use in ESPnet2
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html)
+if you haven't done that already.
+
+```bash
+cd espnet
+git checkout 19787b1793eda2b4007aa5b2c4d03adf6c18abfb
+pip install -e .
+cd egs2/TEMPLATE/spk1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/rats_ska_wavlm_frozen
+```
+
+<!-- Generated by scripts/utils/show_spk_result.py -->
+# RESULTS
+## Environments
+date: 2024-10-04 17:09:51.822703
+
+- python version: 3.9.19 (main, May  6 2024, 19:43:03)  [GCC 11.2.0]
+- espnet version: 202402
+- pytorch version: 1.13.1
+
+| | Mean | Std |
+|---|---|---|
+| Target | -1.0478 | 0.2006 |
+| Non-target | 0.1717 | 0.1717 |
+
+| Model name | EER(%) | minDCF |
+|---|---|---|
+| conf/train_SKA_wavlm_frozen | 19.728 | 0.92968 |
+
+## SPK config
+
+<details><summary>expand</summary>
+
+```
+config: conf/train_SKA_wavlm_frozen.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_SKA_wavlm_frozen_raw_copy
+ngpu: 1
+seed: 0
+num_workers: 6
+num_att_plot: 0
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 57255
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: true
+cudnn_deterministic: 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: 8
+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:
+- frontend.upstream
+num_iters_per_epoch: null
+batch_size: 64
+valid_batch_size: 5
+batch_bins: 1000000
+valid_batch_bins: null
+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_copy/rats_train/wav.scp
+    - speech
+    - sound
+-   - dump/raw_copy/rats_train/utt2spk
+    - spk_labels
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw_copy/rats_test/trial.scp
+    - speech
+    - sound
+-   - dump/raw_copy/rats_test/trial2.scp
+    - speech2
+    - sound
+-   - dump/raw_copy/rats_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: 0.001
+    weight_decay: 5.0e-05
+    amsgrad: false
+scheduler: cosineannealingwarmuprestarts
+scheduler_conf:
+    first_cycle_steps: 71280
+    cycle_mult: 1.0
+    max_lr: 0.001
+    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_copy/rats_train/spk2utt
+spk_num: 5903
+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: ska_tdnn
+encoder_conf:
+    model_scale: 8
+    ndim: 1024
+    ska_dim: 128
+    output_size: 1536
+pooling: chn_attn_stat
+pooling_conf: {}
+projector: ska_tdnn
+projector_conf:
+    output_size: 192
+preprocessor: spk
+preprocessor_conf:
+    target_duration: 3.0
+    sample_rate: 16000
+    num_eval: 5
+    noise_apply_prob: 0.0
+    noise_info: null
+    rir_apply_prob: 0.0
+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
+```
+
+</details>
+
+
+
+### Citing ESPnet
+
+```BibTex
+@inproceedings{watanabe2018espnet,
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  title={{ESPnet}: End-to-End Speech Processing Toolkit},
+  year={2018},
+  booktitle={Proceedings of Interspeech},
+  pages={2207--2211},
+  doi={10.21437/Interspeech.2018-1456},
+  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
+}
+
+
+
+
+
+
+```
+
+or arXiv:
+
+```bibtex
+@misc{watanabe2018espnet,
+  title={ESPnet: End-to-End Speech Processing Toolkit},
+  author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai},
+  year={2018},
+  eprint={1804.00015},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL}
+}
+```

data/user_data/hyejinsh/exp_rats_spk1/spk_train_SKA_wavlm_frozen_raw_copy_sp/39epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5396bf6b1f61acde15e63c8d1e677fb5392d81d253a4ec31045e409c4c4647
+size 2038644970

data/user_data/hyejinsh/exp_rats_spk1/spk_train_SKA_wavlm_frozen_raw_copy_sp/RESULTS.md

@@ -0,0 +1,17 @@
+<!-- Generated by scripts/utils/show_spk_result.py -->
+# RESULTS
+## Environments
+date: 2024-10-04 17:09:51.822703
+
+- python version: 3.9.19 (main, May  6 2024, 19:43:03)  [GCC 11.2.0]
+- espnet version: 202402
+- pytorch version: 1.13.1
+
+| | Mean | Std |
+|---|---|---|
+| Target | -1.0478 | 0.2006 |
+| Non-target | 0.1717 | 0.1717 |
+
+| Model name | EER(%) | minDCF |
+|---|---|---|
+| conf/train_SKA_wavlm_frozen | 19.728 | 0.92968 |

data/user_data/hyejinsh/exp_rats_spk1/spk_train_SKA_wavlm_frozen_raw_copy_sp/config.yaml

@@ -0,0 +1,184 @@
+config: conf/train_SKA_wavlm_frozen.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_SKA_wavlm_frozen_raw_copy
+ngpu: 1
+seed: 0
+num_workers: 6
+num_att_plot: 0
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 57255
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: true
+cudnn_deterministic: 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: 8
+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:
+- frontend.upstream
+num_iters_per_epoch: null
+batch_size: 64
+valid_batch_size: 5
+batch_bins: 1000000
+valid_batch_bins: null
+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_copy/rats_train/wav.scp
+    - speech
+    - sound
+-   - dump/raw_copy/rats_train/utt2spk
+    - spk_labels
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw_copy/rats_test/trial.scp
+    - speech
+    - sound
+-   - dump/raw_copy/rats_test/trial2.scp
+    - speech2
+    - sound
+-   - dump/raw_copy/rats_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: 0.001
+    weight_decay: 5.0e-05
+    amsgrad: false
+scheduler: cosineannealingwarmuprestarts
+scheduler_conf:
+    first_cycle_steps: 71280
+    cycle_mult: 1.0
+    max_lr: 0.001
+    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_copy/rats_train/spk2utt
+spk_num: 5903
+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: ska_tdnn
+encoder_conf:
+    model_scale: 8
+    ndim: 1024
+    ska_dim: 128
+    output_size: 1536
+pooling: chn_attn_stat
+pooling_conf: {}
+projector: ska_tdnn
+projector_conf:
+    output_size: 192
+preprocessor: spk
+preprocessor_conf:
+    target_duration: 3.0
+    sample_rate: 16000
+    num_eval: 5
+    noise_apply_prob: 0.0
+    noise_info: null
+    rir_apply_prob: 0.0
+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

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202402'
+files:
+  model_file: /data/user_data/hyejinsh/exp_rats_spk1/spk_train_SKA_wavlm_frozen_raw_copy_sp/39epoch.pth
+python: "3.9.19 (main, May  6 2024, 19:43:03) \n[GCC 11.2.0]"
+timestamp: 1731353333.451125
+torch: 1.13.1
+yaml_files:
+  train_config: /data/user_data/hyejinsh/exp_rats_spk1/spk_train_SKA_wavlm_frozen_raw_copy_sp/config.yaml