|
|
--- |
|
|
tags: |
|
|
- espnet |
|
|
- audio |
|
|
- classification |
|
|
datasets: |
|
|
- fsd50k |
|
|
license: cc-by-4.0 |
|
|
--- |
|
|
|
|
|
## ESPnet2 CLS model |
|
|
|
|
|
### `espnet/OpenBEATS-Base-i2-fsd50k` |
|
|
|
|
|
This model was trained by Shikhar Bharadwaj using fsd50k recipe in [espnet](https://github.com/espnet/espnet/). |
|
|
|
|
|
## CLS config |
|
|
|
|
|
<details><summary>expand</summary> |
|
|
|
|
|
``` |
|
|
config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/earbasei2/conf/ear_base/fsd50k.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/fsd50k/cls_earbasei2 |
|
|
ngpu: 0 |
|
|
seed: 0 |
|
|
num_workers: 8 |
|
|
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: 105 |
|
|
patience: null |
|
|
val_scheduler_criterion: |
|
|
- valid |
|
|
- loss |
|
|
early_stopping_criterion: |
|
|
- valid |
|
|
- loss |
|
|
- min |
|
|
best_model_criterion: |
|
|
- - valid |
|
|
- epoch_mAP |
|
|
- max |
|
|
keep_nbest_models: 5 |
|
|
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: fsd50k.earbasei2 |
|
|
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: 20 |
|
|
valid_batch_size: null |
|
|
batch_bins: 3000000 |
|
|
valid_batch_bins: null |
|
|
category_sample_size: 10 |
|
|
train_shape_file: |
|
|
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/fsd50k/cls_stats_16k/train/speech_shape |
|
|
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/fsd50k/cls_stats_16k/train/label_shape |
|
|
valid_shape_file: |
|
|
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/fsd50k/cls_stats_16k/valid/speech_shape |
|
|
- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/fsd50k/cls_stats_16k/valid/label_shape |
|
|
batch_type: numel |
|
|
valid_batch_type: null |
|
|
fold_length: |
|
|
- 160000 |
|
|
- 200 |
|
|
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/fsd50k/train/wav.scp |
|
|
- speech |
|
|
- sound |
|
|
- - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/fsd50k/train/text |
|
|
- label |
|
|
- text |
|
|
valid_data_path_and_name_and_type: |
|
|
- - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/fsd50k/val/wav.scp |
|
|
- speech |
|
|
- sound |
|
|
- - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/fsd50k/val/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: 105 |
|
|
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/fsd50k/cls_earbasei2 |
|
|
token_list: |
|
|
- Music |
|
|
- Musical_instrument |
|
|
- Domestic_sounds_and_home_sounds |
|
|
- Human_voice |
|
|
- Animal |
|
|
- Percussion |
|
|
- Wind_instrument_and_woodwind_instrument |
|
|
- Vehicle |
|
|
- Bowed_string_instrument |
|
|
- Plucked_string_instrument |
|
|
- Guitar |
|
|
- Wild_animals |
|
|
- Speech |
|
|
- Keyboard_(musical) |
|
|
- Water |
|
|
- Motor_vehicle_(road) |
|
|
- Alarm |
|
|
- Bird |
|
|
- Drum |
|
|
- Liquid |
|
|
- Explosion |
|
|
- Mechanisms |
|
|
- Domestic_animals_and_pets |
|
|
- Door |
|
|
- Laughter |
|
|
- Brass_instrument |
|
|
- Glass |
|
|
- Engine |
|
|
- Respiratory_sounds |
|
|
- Tools |
|
|
- Bell |
|
|
- Piano |
|
|
- Dog |
|
|
- Human_group_actions |
|
|
- Snare_drum |
|
|
- Car |
|
|
- Cymbal |
|
|
- Rail_transport |
|
|
- Trumpet |
|
|
- Telephone |
|
|
- Hands |
|
|
- Singing |
|
|
- Fart |
|
|
- Acoustic_guitar |
|
|
- Bird_vocalization_and_bird_call_and_bird_song |
|
|
- Rain |
|
|
- Livestock_and_farm_animals_and_working_animals |
|
|
- Electric_guitar |
|
|
- Breathing |
|
|
- Thunderstorm |
|
|
- Thunder |
|
|
- Hi-hat |
|
|
- Coin_(dropping) |
|
|
- Fire |
|
|
- Bark |
|
|
- Shatter |
|
|
- Female_speech_and_woman_speaking |
|
|
- Fireworks |
|
|
- Insect |
|
|
- Male_speech_and_man_speaking |
|
|
- Squeak |
|
|
- Applause |
|
|
- Clapping |
|
|
- Walk_and_footsteps |
|
|
- Splash_and_splatter |
|
|
- Slam |
|
|
- Gunshot_and_gunfire |
|
|
- Drum_kit |
|
|
- Train |
|
|
- Dishes_and_pots_and_pans |
|
|
- Bass_guitar |
|
|
- Organ |
|
|
- Wood |
|
|
- Cat |
|
|
- Subway_and_metro_and_underground |
|
|
- Thump_and_thud |
|
|
- Typing |
|
|
- Camera |
|
|
- Mallet_percussion |
|
|
- Wind |
|
|
- Zipper_(clothing) |
|
|
- Sink_(filling_or_washing) |
|
|
- Water_tap_and_faucet |
|
|
- Cough |
|
|
- Clock |
|
|
- Crowd |
|
|
- Tearing |
|
|
- Whoosh_and_swoosh_and_swish |
|
|
- Knock |
|
|
- Cutlery_and_silverware |
|
|
- Rattle_(instrument) |
|
|
- Writing |
|
|
- Screaming |
|
|
- Chink_and_clink |
|
|
- Ocean |
|
|
- Run |
|
|
- Tap |
|
|
- Fowl |
|
|
- Scratching_(performance_technique) |
|
|
- Drip |
|
|
- Bicycle |
|
|
- Tambourine |
|
|
- Burping_and_eructation |
|
|
- Crackle |
|
|
- Shout |
|
|
- Bass_drum |
|
|
- Bus |
|
|
- Stream |
|
|
- Crash_cymbal |
|
|
- Cheering |
|
|
- Toilet_flush |
|
|
- Gong |
|
|
- Crumpling_and_crinkling |
|
|
- Aircraft |
|
|
- Sliding_door |
|
|
- Chirp_and_tweet |
|
|
- Crushing |
|
|
- Strum |
|
|
- Chime |
|
|
- Chewing_and_mastication |
|
|
- Marimba_and_xylophone |
|
|
- Harp |
|
|
- Cricket |
|
|
- Cowbell |
|
|
- Meow |
|
|
- Motorcycle |
|
|
- Keys_jangling |
|
|
- Whispering |
|
|
- Power_tool |
|
|
- Waves_and_surf |
|
|
- Boom |
|
|
- Drill |
|
|
- Hammer |
|
|
- Harmonica |
|
|
- Accelerating_and_revving_and_vroom |
|
|
- Hiss |
|
|
- Child_speech_and_kid_speaking |
|
|
- Rattle |
|
|
- Drawer_open_or_close |
|
|
- Bathtub_(filling_or_washing) |
|
|
- Trickle_and_dribble |
|
|
- Pour |
|
|
- Microwave_oven |
|
|
- Traffic_noise_and_roadway_noise |
|
|
- Engine_starting |
|
|
- Yell |
|
|
- Chicken_and_rooster |
|
|
- Female_singing |
|
|
- Finger_snapping |
|
|
- Computer_keyboard |
|
|
- Car_passing_by |
|
|
- Gurgling |
|
|
- Raindrop |
|
|
- Crack |
|
|
- Sawing |
|
|
- Vehicle_horn_and_car_horn_and_honking |
|
|
- Truck |
|
|
- Crying_and_sobbing |
|
|
- Idling |
|
|
- Doorbell |
|
|
- Scissors |
|
|
- Boat_and_Water_vehicle |
|
|
- Fixed-wing_aircraft_and_airplane |
|
|
- Giggle |
|
|
- Printer |
|
|
- Cupboard_open_or_close |
|
|
- Tick-tock |
|
|
- Ringtone |
|
|
- Fill_(with_liquid) |
|
|
- Skateboard |
|
|
- Male_singing |
|
|
- Screech |
|
|
- Church_bell |
|
|
- Buzz |
|
|
- Siren |
|
|
- Crow |
|
|
- Sigh |
|
|
- Race_car_and_auto_racing |
|
|
- Growling |
|
|
- Frog |
|
|
- Gull_and_seagull |
|
|
- Packing_tape_and_duct_tape |
|
|
- Bicycle_bell |
|
|
- Frying_(food) |
|
|
- Chatter |
|
|
- Boiling |
|
|
- Wind_chime |
|
|
- Sneeze |
|
|
- Mechanical_fan |
|
|
- Purr |
|
|
- Speech_synthesizer |
|
|
- Conversation |
|
|
- Ratchet_and_pawl |
|
|
- Gasp |
|
|
- Chuckle_and_chortle |
|
|
- Glockenspiel |
|
|
- Accordion |
|
|
- Tabla |
|
|
- Typewriter |
|
|
- Tick |
|
|
- <blank> |
|
|
- <unk> |
|
|
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/model_checkpoints/ear_base/beats_iter1_base.tune_lr5e-4_warmup40000_bins1600000_totalsteps400000/epoch59.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 |
|
|
text_encoder: null |
|
|
text_encoder_conf: {} |
|
|
embedding_fusion: null |
|
|
embedding_fusion_conf: {} |
|
|
decoder: linear |
|
|
decoder_conf: {} |
|
|
model: espnet |
|
|
model_conf: |
|
|
classification_type: multi-label |
|
|
mixup_probability: 0.2 |
|
|
lsm_weight: 0.0 |
|
|
log_epoch_metrics: true |
|
|
user_callbacks: |
|
|
- mAP_logging |
|
|
required: |
|
|
- output_dir |
|
|
- token_list |
|
|
task: cls |
|
|
``` |
|
|
|
|
|
</details> |
|
|
|
|
|
### Citations |
|
|
|
|
|
```BibTex |
|
|
|
|
|
@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} |
|
|
} |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
``` |
|
|
|
