Sponsored by APIMart
Toolify Toolify logo
AI Models
OpenBEATS-Large-i3-enabirds

espnet / OpenBEATS-Large-i3-enabirds

Run on huggingface.co
huggingface.co
Total runs: 11
24-hour runs: 0
7-day runs: -2
30-day runs: 0
Model's Last Updated: September 18 2026
audio-classification

Introduction of OpenBEATS-Large-i3-enabirds

Model Details of OpenBEATS-Large-i3-enabirds

ESPnet2 CLS model
espnet/OpenBEATS-Large-i3-enabirds

This model was trained by Shikhar Bharadwaj using beans recipe in espnet .

CLS config
expand 
config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/earlarge3/conf/ear_large/beans_enabirds.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_earlarge3
ngpu: 0
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: null
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
gradient_as_bucket_view: true
ddp_comm_hook: 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
    - epoch_mAP
    - 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: true
wandb_project: audioverse
wandb_id: null
wandb_entity: shikhar
wandb_name: beans_enabirds.earlarge3
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:
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_stats_16k/train/speech_shape
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_stats_16k/train/label_shape
valid_shape_file:
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_stats_16k/valid/speech_shape
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_stats_16k/valid/label_shape
batch_type: folded
valid_batch_type: null
fold_length:
- 160000
- 35
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
utt2weight_file: null
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:
-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/beans_enabirds/enabirds.train/wav.scp
    - speech
    - sound
-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/beans_enabirds/enabirds.train/text
    - label
    - text
valid_data_path_and_name_and_type:
-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/beans_enabirds/enabirds.dev/wav.scp
    - speech
    - sound
-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/beans_enabirds/enabirds.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
lightning_conf:
    log_every_n_steps: 250
    max_epochs: 250
    strategy: ddp
    strategy_conf:
        find_unused_parameters: true
    best_model_criterion:
    -   - valid/epoch_mAP
        - max
        - 1
    devices: 1
    num_nodes: 1
    default_root_dir: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/beans_enabirds/cls_earlarge3
token_list:
- eato
- amcr
- woth
- noca
- btnw
- bcch
- tuti
- oven
- revi
- coye
- blja
- scta
- amre
- bggn
- kewa
- bhco
- baww
- heth
- bhvi
- rbwo
- nofl
- howa
- ybcu
- bwwa
- carw
- amgo
- rbgr
- rcki
- amro
- lowa
- swth
- wbnu
- witu
- dowo
- cang
- hawo
- cswa
- rwbl
- rsha
- bbwa
- baor
- piwo
- brcr
- cora
- nawa
- <unk>
- <blank>
text_token_list: null
text_bpemodel: null
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: /work/nvme/bbjs/sbharadwaj/7Msounds/exp/beats_iter2_large2.tune_lr1.0e-4_warmup40000_bins1600000_totalsteps400000/epoch_latest.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: false
text_encoder: null
text_encoder_conf: {}
embedding_fusion: null
embedding_fusion_conf: {}
decoder: linear
decoder_conf: {}
model: espnet
model_conf:
    classification_type: multi-label
    log_epoch_metrics: true
user_callbacks:
- mAP_logging
required:
- output_dir
- token_list
task: cls
Citations 

@article{bharadwaj2025openbeats,
  title={OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder},
  author={Bharadwaj, Shikhar and Cornell, Samuele and Choi, Kwanghee and Fukayama, Satoru and Shim, Hye-jin and Deshmukh, Soham and Watanabe, Shinji},
  journal={arXiv preprint arXiv:2507.14129},
  year={2025}
}

@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}
}

Runs of espnet OpenBEATS-Large-i3-enabirds on huggingface.co

11
Total runs
0
24-hour runs
0
3-day runs
-2
7-day runs
0
30-day runs

More Information About OpenBEATS-Large-i3-enabirds huggingface.co Model

More OpenBEATS-Large-i3-enabirds license Visit here:

https://choosealicense.com/licenses/cc-by-4.0

OpenBEATS-Large-i3-enabirds huggingface.co

OpenBEATS-Large-i3-enabirds huggingface.co is an AI model on huggingface.co that provides OpenBEATS-Large-i3-enabirds's model effect (), which can be used instantly with this espnet OpenBEATS-Large-i3-enabirds model. huggingface.co supports a free trial of the OpenBEATS-Large-i3-enabirds model, and also provides paid use of the OpenBEATS-Large-i3-enabirds. Support call OpenBEATS-Large-i3-enabirds model through api, including Node.js, Python, http.

OpenBEATS-Large-i3-enabirds huggingface.co Url

https://huggingface.co/espnet/OpenBEATS-Large-i3-enabirds

espnet OpenBEATS-Large-i3-enabirds online free

OpenBEATS-Large-i3-enabirds huggingface.co is an online trial and call api platform, which integrates OpenBEATS-Large-i3-enabirds's modeling effects, including api services, and provides a free online trial of OpenBEATS-Large-i3-enabirds, you can try OpenBEATS-Large-i3-enabirds online for free by clicking the link below.

espnet OpenBEATS-Large-i3-enabirds online free url in huggingface.co:

https://huggingface.co/espnet/OpenBEATS-Large-i3-enabirds

OpenBEATS-Large-i3-enabirds install

OpenBEATS-Large-i3-enabirds is an open source model from GitHub that offers a free installation service, and any user can find OpenBEATS-Large-i3-enabirds on GitHub to install. At the same time, huggingface.co provides the effect of OpenBEATS-Large-i3-enabirds install, users can directly use OpenBEATS-Large-i3-enabirds installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

OpenBEATS-Large-i3-enabirds install url in huggingface.co:

https://huggingface.co/espnet/OpenBEATS-Large-i3-enabirds

Url of OpenBEATS-Large-i3-enabirds

OpenBEATS-Large-i3-enabirds huggingface.co Url

Provider of OpenBEATS-Large-i3-enabirds huggingface.co

espnet
ORGANIZATIONS
huggingface.co

Other API from espnet

 huggingface.co
espnet/owsm_ctc_v4_1B

Total runs: 11.0K
Run Growth: -1.2K
Growth Rate: -10.58%
Updated:October 11 2026
huggingface.co
espnet/hubert_dummy

Total runs: 3.2K
Run Growth: -2.4K
Growth Rate: -68.99%
Updated:September 18 2026
huggingface.co
espnet/powsm

Total runs: 238
Run Growth: 125
Growth Rate: 52.52%
Updated:January 22 2026
huggingface.co
espnet/powsm_ctc

Total runs: 185
Run Growth: 117
Growth Rate: 63.24%
Updated:September 20 2026
huggingface.co
espnet/owsm_v3.1_ebf

Total runs: 126
Run Growth: 66
Growth Rate: 51.16%
Updated:October 11 2026
huggingface.co
espnet/xeus

Total runs: 84
Run Growth: 44
Growth Rate: 46.81%
Updated:June 17 2025
huggingface.co
espnet/owls_9B_180K

Total runs: 20
Run Growth: 16
Growth Rate: 84.21%
Updated:May 03 2025
huggingface.co
espnet/owsm_v3

Total runs: 20
Run Growth: 12
Growth Rate: 50.00%
Updated:October 11 2026
huggingface.co
espnet/owsm_v3.2

Total runs: 14
Run Growth: 4
Growth Rate: 28.57%
Updated:August 26 2024
huggingface.co
espnet/owls_1B_180K

Total runs: 13
Run Growth: 3
Growth Rate: 25.00%
Updated:May 03 2025