--- tags: - espnet - audio - classification language: en datasets: - bean license: cc-by-4.0 --- ## ESPnet2 CLS model ### `espnet/BEATs-BEAN.HumBugDB` This model was trained by Shikhar Bharadwaj using bean 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 9191aa59acc7d3ceaca1f48dcc8fbdad2e03484b pip install -e . cd egs2/bean/cls1 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/BEATs-BEAN.HumBugDB ``` # RESULTS ## Environments - date: `Tue Jan 7 19:11:31 EST 2025` - python version: `3.9.20 (main, Oct 3 2024, 07:27:41) [GCC 11.2.0]` - espnet version: `espnet 202412` - pytorch version: `pytorch 2.4.0` - Git hash: `9191aa59acc7d3ceaca1f48dcc8fbdad2e03484b` - Commit date: `Tue Jan 7 04:34:03 2025 -0500` ## cls_humbugdb.20250107.141123 |Dataset|Metric|Value| |---|---|---| /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.dev/score|mean_acc|86.35 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.dev/score|mAP|66.74 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.dev/score|mean_auc|96.32 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.dev/score|n_labels|14.00 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.dev/score|n_instances|1604.00 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.test/score|mean_acc|80.63 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.test/score|mAP|67.20 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.test/score|mean_auc|94.15 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.test/score|n_labels|14.00 /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123/cls_humbugdb.test/score|n_instances|1859.00 ## CLS config
expand ``` config: conf/beats_humbugdb.yaml print_config: false log_level: INFO drop_last_iter: false dry_run: false iterator_type: sequence valid_iterator_type: null output_dir: /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_humbugdb.20250107.141123 ngpu: 1 seed: 0 num_workers: 2 num_att_plot: 0 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: true 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: 250 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - acc - max keep_nbest_models: 1 nbest_averaging_interval: 0 grad_clip: 1 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: null batch_size: 32 valid_batch_size: 32 batch_bins: 1000000 valid_batch_bins: null category_sample_size: 10 train_shape_file: - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_stats_16k/train/speech_shape - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_stats_16k/train/label_shape valid_shape_file: - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_stats_16k/valid/speech_shape - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/exp/cls_stats_16k/valid/label_shape batch_type: folded valid_batch_type: null fold_length: - 160000 - 5 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: - - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/dump/humbugdb.train/wav.scp - speech - sound - - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/dump/humbugdb.train/text - label - text valid_data_path_and_name_and_type: - - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/dump/humbugdb.dev/wav.scp - speech - sound - - /compute/babel-11-13/sbharad2/beats_run/bean.humbugdb/dump/humbugdb.dev/text - label - 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: 3.0e-05 weight_decay: 0.01 betas: - 0.9 - 0.98 scheduler: cosineannealingwarmuprestarts scheduler_conf: first_cycle_steps: 95000 warmup_steps: 8000 max_lr: 3.0e-05 min_lr: 5.0e-06 token_list: - non-mosquito - an_arabiensis - an_gambiae_ss - others - culex_quinquefasciatus - culex_pipiens_complex - an_funestus_ss - an_squamosus - ma_uniformis - an_dirus - an_harrisoni - an_maculatus - ae_aegypti - an_funestus_sl - token_type: word init: xavier_normal input_size: 1 use_preprocessor: true frontend: null frontend_conf: {} specaug: null specaug_conf: {} normalize: null normalize_conf: {} preencoder: null preencoder_conf: {} encoder: beats encoder_conf: beats_ckpt_path: /compute/babel-13-33/sbharad2/models/BEATs/BEATs_iter3.pt beats_config: layer_wise_gradient_decay_ratio: 0.3 encoder_layerdrop: 0.1 dropout: 0.0 use_weighted_representation: false specaug_config: apply_time_warp: true apply_freq_mask: false apply_time_mask: true time_mask_width_ratio_range: - 0 - 0.06 num_time_mask: 1 roll_augment: true roll_interval: 1 decoder: linear decoder_conf: {} model: espnet model_conf: classification_type: multi-class mixup_augmentation: false lsm_weight: 0.1 required: - output_dir - token_list version: '202412' distributed: false ```
### 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} } ```