Add model files

exp/diar_stats_8k/train/feats_lengths_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488ffa7ae62201b12edef41fc97c4787f5a6be32bb03725f551f376e0abb3301
+size 778

exp/diar_stats_8k/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398b81c5d3e1ee8674d9776150f59b1ecd02b61958485048f4589ce879e1de8a
+size 946

exp/diar_train_diar_raw/500epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c456775d4e4ae3d9d9a2dbb5b02d956a6d003e94e7f41230de1463bdf1818f
+size 8834948

exp/diar_train_diar_raw/RESULTS.md

@@ -0,0 +1,40 @@
+<!-- Generated by scripts/utils/show_diar_result.sh -->
+# RESULTS
+## Environments
+- date: `Thu Dec 19 22:03:53 EST 2024`
+- python version: `3.11.10 (main, Oct  3 2024, 07:29:13) [GCC 11.2.0]`
+- espnet version: `espnet 202409`
+- pytorch version: `pytorch 2.4.0`
+- Git hash: `c12b3d59ca4fd8847edf274e56a1716474d2a30e`
+  - Commit date: `Thu Dec 19 21:58:26 2024 -0500`
+
+## diar_train_diar_raw
+### DER
+diarized_test
+|threshold_median_collar|DER|
+|---|---|
+|result_th0.3_med11_collar0.0|71.73|
+|result_th0.3_med1_collar0.0|74.62|
+|result_th0.4_med11_collar0.0|70.10|
+|result_th0.4_med1_collar0.0|71.98|
+|result_th0.5_med11_collar0.0|70.57|
+|result_th0.5_med1_collar0.0|72.44|
+|result_th0.6_med11_collar0.0|72.64|
+|result_th0.6_med1_collar0.0|74.63|
+|result_th0.7_med11_collar0.0|76.52|
+|result_th0.7_med1_collar0.0|78.41|
+## diar_train_diar_raw
+### DER
+diarized_dev
+|threshold_median_collar|DER|
+|---|---|
+|result_th0.3_med11_collar0.0|75.88|
+|result_th0.3_med1_collar0.0|78.21|
+|result_th0.4_med11_collar0.0|71.45|
+|result_th0.4_med1_collar0.0|73.32|
+|result_th0.5_med11_collar0.0|70.53|
+|result_th0.5_med1_collar0.0|72.34|
+|result_th0.6_med11_collar0.0|72.03|
+|result_th0.6_med1_collar0.0|73.96|
+|result_th0.7_med11_collar0.0|76.66|
+|result_th0.7_med1_collar0.0|78.33|

exp/diar_train_diar_raw/config.yaml

@@ -0,0 +1,180 @@
+config: conf/train_diar.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/diar_train_diar_raw
+ngpu: 1
+seed: 0
+num_workers: 0
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: null
+dist_rank: null
+local_rank: 0
+dist_master_addr: null
+dist_master_port: null
+dist_launcher: null
+multiprocessing_distributed: false
+unused_parameters: false
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 500
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 2
+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: null
+batch_size: 64
+valid_batch_size: 16
+batch_bins: 1000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/diar_stats_8k/train/speech_shape
+- exp/diar_stats_8k/train/spk_labels_shape
+valid_shape_file:
+- exp/diar_stats_8k/valid/speech_shape
+- exp/diar_stats_8k/valid/spk_labels_shape
+batch_type: unsorted
+valid_batch_type: unsorted
+fold_length:
+- 80000
+- 800
+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/train/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train/espnet_rttm
+    - spk_labels
+    - rttm
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/dev/espnet_rttm
+    - spk_labels
+    - rttm
+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: 0.0002
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 100000
+num_spk: 4
+init: xavier_uniform
+input_size: 322
+model_conf:
+    diar_weight: 1.0
+    attractor_weight: 1.0
+    context_size: 7
+    subsampling: 10
+use_preprocessor: true
+frontend: default
+frontend_conf:
+    fs: 8k
+    n_fft: 200
+    win_length: 200
+    hop_length: 128
+    n_mels: 23
+specaug: specaug
+specaug_conf:
+    apply_time_warp: false
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/diar_stats_8k/train/feats_stats.npz
+encoder: transformer
+encoder_conf:
+    input_layer: linear
+    num_blocks: 4
+    linear_units: 512
+    dropout_rate: 0.1
+    output_size: 256
+    attention_heads: 4
+    attention_dropout_rate: 0.1
+decoder: linear
+decoder_conf: {}
+label_aggregator: label_aggregator
+label_aggregator_conf: {}
+attractor: null
+attractor_conf: {}
+required:
+- output_dir
+version: '202409'
+distributed: false