Update model

README.md

@@ -0,0 +1,783 @@
+---
+tags:
+- espnet
+- audio
+- classification
+datasets:
+- as20k
+license: cc-by-4.0
+---
+
+## ESPnet2 CLS model
+
+### `espnet/OpenBEATS-Base-i3-as20k`
+
+This model was trained by Shikhar Bharadwaj using as20k recipe in [espnet](https://github.com/espnet/espnet/).
+
+## CLS config
+
+<details><summary>expand</summary>
+
+```
+config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/earbasei3/conf/ear_base/audioset20k.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/audioset20k/cls_earbasei3
+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: 160
+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: audioset20k.earbasei3
+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: 80
+valid_batch_size: 1200
+batch_bins: 1000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/speech_shape
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/label_shape
+valid_shape_file:
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/speech_shape
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/label_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 160000
+- 600
+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/audioset20k/train/wav.scp
+    - speech
+    - sound
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/train/text
+    - label
+    - text
+valid_data_path_and_name_and_type:
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/val/wav.scp
+    - speech
+    - sound
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/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: 500
+    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/audioset20k/cls_earbasei3
+token_list:
+- Music
+- Speech
+- Vehicle
+- Inside,_small_room
+- Animal
+- Musical_instrument
+- Singing
+- Domestic_animals,_pets
+- Guitar
+- Plucked_string_instrument
+- Water
+- Car
+- Dog
+- Percussion
+- Wind_instrument,_woodwind_instrument
+- Outside,_urban_or_manmade
+- Outside,_rural_or_natural
+- Boat,_Water_vehicle
+- Brass_instrument
+- Fowl
+- Drum
+- Siren
+- Engine
+- Bird
+- Insect
+- Gunshot,_gunfire
+- Wood
+- Rail_transport
+- Train
+- Wind
+- Inside,_large_room_or_hall
+- Railroad_car,_train_wagon
+- Child_speech,_kid_speaking
+- Crowd
+- Rub
+- Keyboard_(musical)
+- Wind_noise_(microphone)
+- Pizzicato
+- Emergency_vehicle
+- Bird_vocalization,_bird_call,_bird_song
+- Livestock,_farm_animals,_working_animals
+- Cat
+- Organ
+- Fly,_housefly
+- Mechanisms
+- Bowed_string_instrument
+- Rain
+- Laughter
+- Aircraft
+- Electronic_music
+- Effects_unit
+- Hum
+- Tools
+- Drum_kit
+- Snare_drum
+- Hiss
+- Piano
+- Water_tap,_faucet
+- Rimshot
+- Bass_drum
+- Chicken,_rooster
+- Marimba,_xylophone
+- Horse
+- Song
+- Quack
+- Power_tool
+- Heart_sounds,_heartbeat
+- Goose
+- Hammond_organ
+- Rock_music
+- Ocean
+- Mains_hum
+- Thunder
+- Chime
+- Electronic_dance_music
+- Typing
+- Sink_(filling_or_washing)
+- Raindrop
+- Cello
+- Electric_guitar
+- Cheering
+- Church_bell
+- Christian_music
+- Drum_roll
+- Trombone
+- Glockenspiel
+- Trumpet
+- Cymbal
+- Tabla
+- Clickety-clack
+- Cricket
+- Steam_whistle
+- Explosion
+- Saxophone
+- Thunderstorm
+- Pop_music
+- Zither
+- Applause
+- Choir
+- Whack,_thwack
+- Clarinet
+- Camera
+- Electric_piano
+- Independent_music
+- Fire
+- Frog
+- Jet_engine
+- Music_of_Asia
+- Ding
+- Waves,_surf
+- Cattle,_bovinae
+- Turkey
+- Television
+- Coo
+- Scratching_(performance_technique)
+- Flute
+- Liquid
+- Harp
+- Progressive_rock
+- Happy_music
+- Steel_guitar,_slide_guitar
+- Whoosh,_swoosh,_swish
+- Boom
+- Breathing
+- Electronic_organ
+- Environmental_noise
+- Distortion
+- Alarm_clock
+- Fixed-wing_aircraft,_airplane
+- Violin,_fiddle
+- Whistling
+- Accordion
+- Disco
+- Pump_(liquid)
+- Waterfall
+- Beep,_bleep
+- Blues
+- Grunge
+- Hip_hop_music
+- Whistle
+- Fusillade
+- Splash,_splatter
+- Gush
+- Toothbrush
+- Knock
+- Gargling
+- Snoring
+- Hammer
+- Gobble
+- Walk,_footsteps
+- Jackhammer
+- Filing_(rasp)
+- Snort
+- Narration,_monologue
+- Tire_squeal
+- Fire_alarm
+- Squeal
+- Meow
+- Caterwaul
+- Cutlery,_silverware
+- Mantra
+- Opera
+- Classical_music
+- Theremin
+- Burst,_pop
+- Drip
+- Tick
+- Children_shouting
+- Creak
+- Hiccup
+- Pigeon,_dove
+- Bicycle_bell
+- Baby_cry,_infant_cry
+- Duck
+- Fireworks
+- Tambourine
+- Rodents,_rats,_mice
+- Buzzer
+- Splinter
+- Writing
+- Goat
+- Sheep
+- Heavy_metal
+- Ska
+- Neigh,_whinny
+- Sizzle
+- Rowboat,_canoe,_kayak
+- Wood_block
+- Clang
+- Door
+- Female_singing
+- Stream
+- Chant
+- Vocal_music
+- Yodeling
+- Bee,_wasp,_etc.
+- Air_brake
+- Whir
+- Bird_flight,_flapping_wings
+- French_horn
+- Telephone_dialing,_DTMF
+- Squeak
+- Sitar
+- Smoke_detector,_smoke_alarm
+- Tick-tock
+- Gurgling
+- Bellow
+- Harmonic
+- Male_singing
+- Giggle
+- Bark
+- Vibration
+- Drill
+- Skidding
+- Scratch
+- Drawer_open_or_close
+- Chop
+- Drum_machine
+- Squish
+- Toilet_flush
+- Fart
+- Basketball_bounce
+- Electronic_tuner
+- Singing_bowl
+- Squawk
+- Conversation
+- Reggae
+- Funny_music
+- Scrape
+- Sewing_machine
+- Tender_music
+- Swing_music
+- Dishes,_pots,_and_pans
+- Sampler
+- Synthesizer
+- Clapping
+- Hubbub,_speech_noise,_speech_babble
+- Engine_knocking
+- Canidae,_dogs,_wolves
+- Chainsaw
+- Pour
+- Croak
+- Chewing,_mastication
+- Cowbell
+- Propeller,_airscrew
+- Didgeridoo
+- Ringtone
+- Rattle_(instrument)
+- Artillery_fire
+- Cash_register
+- Crack
+- Growling
+- Mosquito
+- Carnatic_music
+- Honk
+- Howl
+- Cacophony
+- Gospel_music
+- Firecracker
+- Strum
+- Motorboat,_speedboat
+- Clock
+- Dance_music
+- Microwave_oven
+- Country
+- Bluegrass
+- Rattle
+- Mallet_percussion
+- Computer_keyboard
+- Bass_guitar
+- Electric_shaver,_electric_razor
+- Sawing
+- Owl
+- Whip
+- White_noise
+- Chirp_tone
+- Boiling
+- Ship
+- Mouse
+- Breaking
+- Silence
+- Throat_clearing
+- Bleat
+- Salsa_music
+- Patter
+- Vibraphone
+- Flap
+- Typewriter
+- Change_ringing_(campanology)
+- Trickle,_dribble
+- Video_game_music
+- Glass
+- Dial_tone
+- Radio
+- Bell
+- Moo
+- Heart_murmur
+- Clatter
+- Sniff
+- Double_bass
+- Background_music
+- Lawn_mower
+- Printer
+- House_music
+- Tearing
+- Angry_music
+- Male_speech,_man_speaking
+- Wild_animals
+- Cupboard_open_or_close
+- Harpsichord
+- Light_engine_(high_frequency)
+- Child_singing
+- Zipper_(clothing)
+- Jazz
+- Belly_laugh
+- Roar
+- Motor_vehicle_(road)
+- Crowing,_cock-a-doodle-doo
+- Cluck
+- Sad_music
+- Hi-hat
+- Cough
+- Stomach_rumble
+- Alarm
+- String_section
+- Sonar
+- Keys_jangling
+- Synthetic_singing
+- Rapping
+- Sidetone
+- Orchestra
+- Throbbing
+- Whale_vocalization
+- Thunk
+- Children_playing
+- Snake
+- Chink,_clink
+- Chirp,_tweet
+- Boing
+- Shuffle
+- Pulse
+- Punk_rock
+- Crow
+- Caw
+- Static
+- Clicking
+- Snicker
+- Whispering
+- Pink_noise
+- Crushing
+- Wedding_music
+- Crumpling,_crinkling
+- Crackle
+- Whoop
+- Electric_toothbrush
+- Train_wheels_squealing
+- Yell
+- Wind_chime
+- Frying_(food)
+- Christmas_music
+- Fill_(with_liquid)
+- Reverberation
+- Beatboxing
+- Harmonica
+- Banjo
+- Sliding_door
+- Groan
+- Bagpipes
+- Spray
+- Stir
+- Acoustic_guitar
+- Tap
+- Chorus_effect
+- Noise
+- Crunch
+- Biting
+- Aircraft_engine
+- Busy_signal
+- Bang
+- Techno
+- Tuning_fork
+- Tapping_(guitar_technique)
+- Pig
+- Maraca
+- Vacuum_cleaner
+- Mandolin
+- Electronica
+- Theme_music
+- Yip
+- A_capella
+- Rustle
+- Chatter
+- Traditional_music
+- Soul_music
+- Rustling_leaves
+- Afrobeat
+- Hoot
+- Slosh
+- Roaring_cats_(lions,_tigers)
+- Chopping_(food)
+- Heavy_engine_(low_frequency)
+- Sine_wave
+- Speech_synthesizer
+- Middle_Eastern_music
+- Music_of_Latin_America
+- Arrow
+- Timpani
+- Eruption
+- Shofar
+- Jingle_bell
+- Humming
+- Sanding
+- Female_speech,_woman_speaking
+- Gong
+- Rain_on_surface
+- Pant
+- Dubstep
+- Clip-clop
+- Finger_snapping
+- Blender
+- Drum_and_bass
+- Bouncing
+- Vehicle_horn,_car_horn,_honking
+- Slam
+- Idling
+- Rhythm_and_blues
+- Race_car,_auto_racing
+- Single-lens_reflex_camera
+- Smash,_crash
+- Purr
+- Shatter
+- Steelpan
+- Whimper_(dog)
+- Power_windows,_electric_windows
+- Battle_cry
+- Scary_music
+- Hands
+- Echo
+- Truck
+- Buzz
+- Mechanical_fan
+- Plop
+- Run
+- Gasp
+- Psychedelic_rock
+- Grunt
+- Helicopter
+- Dental_drill,_dentist's_drill
+- Babbling
+- Zing
+- Oink
+- Soundtrack_music
+- Ambulance_(siren)
+- Exciting_music
+- Telephone
+- Jingle_(music)
+- Tubular_bells
+- Burping,_eructation
+- Baby_laughter
+- Ping
+- Bow-wow
+- Foghorn
+- Machine_gun
+- Ukulele
+- Telephone_bell_ringing
+- Pulleys
+- Gears
+- Sigh
+- Coin_(dropping)
+- Music_of_Africa
+- Scissors
+- Inside,_public_space
+- Trance_music
+- Roll
+- Thump,_thud
+- Air_conditioning
+- Ding-dong
+- Ratchet,_pawl
+- Hair_dryer
+- Shout
+- Ambient_music
+- Music_for_children
+- Toot
+- Bathtub_(filling_or_washing)
+- Slap,_smack
+- Chuckle,_chortle
+- Traffic_noise,_roadway_noise
+- Bicycle
+- Whimper
+- Doorbell
+- Wheeze
+- Sailboat,_sailing_ship
+- Cap_gun
+- Wail,_moan
+- Rock_and_roll
+- Jingle,_tinkle
+- Fire_engine,_fire_truck_(siren)
+- Funk
+- Lullaby
+- Field_recording
+- Skateboard
+- Steam
+- Rumble
+- Medium_engine_(mid_frequency)
+- Sound_effect
+- Flamenco
+- Shuffling_cards
+- Subway,_metro,_underground
+- Police_car_(siren)
+- Folk_music
+- Crying,_sobbing
+- New-age_music
+- Ice_cream_truck,_ice_cream_van
+- Music_of_Bollywood
+- Accelerating,_revving,_vroom
+- Screaming
+- Motorcycle
+- Engine_starting
+- Train_whistle
+- Car_passing_by
+- Bus
+- Sneeze
+- Train_horn
+- Air_horn,_truck_horn
+- Civil_defense_siren
+- Car_alarm
+- Reversing_beeps
+- <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/7Msounds/exp/beats_iter2_base2.tune_lr5e-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: 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: 0.8
+    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}
+}
+
+
+
+
+
+
+```

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202503'
+files:
+  classification_model_file: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/valid.epoch_mAP.ave_1best.pth
+python: "3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 17:20:25) \n[GCC 12.3.0]"
+timestamp: 1763330905.304442
+torch: 2.1.2
+yaml_files:
+  classification_train_config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/config.yaml

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/data/audioset20k/token_list

@@ -0,0 +1,529 @@
+Music
+Speech
+Vehicle
+Inside,_small_room
+Animal
+Musical_instrument
+Singing
+Domestic_animals,_pets
+Guitar
+Plucked_string_instrument
+Water
+Car
+Dog
+Percussion
+Wind_instrument,_woodwind_instrument
+Outside,_urban_or_manmade
+Outside,_rural_or_natural
+Boat,_Water_vehicle
+Brass_instrument
+Fowl
+Drum
+Siren
+Engine
+Bird
+Insect
+Gunshot,_gunfire
+Wood
+Rail_transport
+Train
+Wind
+Inside,_large_room_or_hall
+Railroad_car,_train_wagon
+Child_speech,_kid_speaking
+Crowd
+Rub
+Keyboard_(musical)
+Wind_noise_(microphone)
+Pizzicato
+Emergency_vehicle
+Bird_vocalization,_bird_call,_bird_song
+Livestock,_farm_animals,_working_animals
+Cat
+Organ
+Fly,_housefly
+Mechanisms
+Bowed_string_instrument
+Rain
+Laughter
+Aircraft
+Electronic_music
+Effects_unit
+Hum
+Tools
+Drum_kit
+Snare_drum
+Hiss
+Piano
+Water_tap,_faucet
+Rimshot
+Bass_drum
+Chicken,_rooster
+Marimba,_xylophone
+Horse
+Song
+Quack
+Power_tool
+Heart_sounds,_heartbeat
+Goose
+Hammond_organ
+Rock_music
+Ocean
+Mains_hum
+Thunder
+Chime
+Electronic_dance_music
+Typing
+Sink_(filling_or_washing)
+Raindrop
+Cello
+Electric_guitar
+Cheering
+Church_bell
+Christian_music
+Drum_roll
+Trombone
+Glockenspiel
+Trumpet
+Cymbal
+Tabla
+Clickety-clack
+Cricket
+Steam_whistle
+Explosion
+Saxophone
+Thunderstorm
+Pop_music
+Zither
+Applause
+Choir
+Whack,_thwack
+Clarinet
+Camera
+Electric_piano
+Independent_music
+Fire
+Frog
+Jet_engine
+Music_of_Asia
+Ding
+Waves,_surf
+Cattle,_bovinae
+Turkey
+Television
+Coo
+Scratching_(performance_technique)
+Flute
+Liquid
+Harp
+Progressive_rock
+Happy_music
+Steel_guitar,_slide_guitar
+Whoosh,_swoosh,_swish
+Boom
+Breathing
+Electronic_organ
+Environmental_noise
+Distortion
+Alarm_clock
+Fixed-wing_aircraft,_airplane
+Violin,_fiddle
+Whistling
+Accordion
+Disco
+Pump_(liquid)
+Waterfall
+Beep,_bleep
+Blues
+Grunge
+Hip_hop_music
+Whistle
+Fusillade
+Splash,_splatter
+Gush
+Toothbrush
+Knock
+Gargling
+Snoring
+Hammer
+Gobble
+Walk,_footsteps
+Jackhammer
+Filing_(rasp)
+Snort
+Narration,_monologue
+Tire_squeal
+Fire_alarm
+Squeal
+Meow
+Caterwaul
+Cutlery,_silverware
+Mantra
+Opera
+Classical_music
+Theremin
+Burst,_pop
+Drip
+Tick
+Children_shouting
+Creak
+Hiccup
+Pigeon,_dove
+Bicycle_bell
+Baby_cry,_infant_cry
+Duck
+Fireworks
+Tambourine
+Rodents,_rats,_mice
+Buzzer
+Splinter
+Writing
+Goat
+Sheep
+Heavy_metal
+Ska
+Neigh,_whinny
+Sizzle
+Rowboat,_canoe,_kayak
+Wood_block
+Clang
+Door
+Female_singing
+Stream
+Chant
+Vocal_music
+Yodeling
+Bee,_wasp,_etc.
+Air_brake
+Whir
+Bird_flight,_flapping_wings
+French_horn
+Telephone_dialing,_DTMF
+Squeak
+Sitar
+Smoke_detector,_smoke_alarm
+Tick-tock
+Gurgling
+Bellow
+Harmonic
+Male_singing
+Giggle
+Bark
+Vibration
+Drill
+Skidding
+Scratch
+Drawer_open_or_close
+Chop
+Drum_machine
+Squish
+Toilet_flush
+Fart
+Basketball_bounce
+Electronic_tuner
+Singing_bowl
+Squawk
+Conversation
+Reggae
+Funny_music
+Scrape
+Sewing_machine
+Tender_music
+Swing_music
+Dishes,_pots,_and_pans
+Sampler
+Synthesizer
+Clapping
+Hubbub,_speech_noise,_speech_babble
+Engine_knocking
+Canidae,_dogs,_wolves
+Chainsaw
+Pour
+Croak
+Chewing,_mastication
+Cowbell
+Propeller,_airscrew
+Didgeridoo
+Ringtone
+Rattle_(instrument)
+Artillery_fire
+Cash_register
+Crack
+Growling
+Mosquito
+Carnatic_music
+Honk
+Howl
+Cacophony
+Gospel_music
+Firecracker
+Strum
+Motorboat,_speedboat
+Clock
+Dance_music
+Microwave_oven
+Country
+Bluegrass
+Rattle
+Mallet_percussion
+Computer_keyboard
+Bass_guitar
+Electric_shaver,_electric_razor
+Sawing
+Owl
+Whip
+White_noise
+Chirp_tone
+Boiling
+Ship
+Mouse
+Breaking
+Silence
+Throat_clearing
+Bleat
+Salsa_music
+Patter
+Vibraphone
+Flap
+Typewriter
+Change_ringing_(campanology)
+Trickle,_dribble
+Video_game_music
+Glass
+Dial_tone
+Radio
+Bell
+Moo
+Heart_murmur
+Clatter
+Sniff
+Double_bass
+Background_music
+Lawn_mower
+Printer
+House_music
+Tearing
+Angry_music
+Male_speech,_man_speaking
+Wild_animals
+Cupboard_open_or_close
+Harpsichord
+Light_engine_(high_frequency)
+Child_singing
+Zipper_(clothing)
+Jazz
+Belly_laugh
+Roar
+Motor_vehicle_(road)
+Crowing,_cock-a-doodle-doo
+Cluck
+Sad_music
+Hi-hat
+Cough
+Stomach_rumble
+Alarm
+String_section
+Sonar
+Keys_jangling
+Synthetic_singing
+Rapping
+Sidetone
+Orchestra
+Throbbing
+Whale_vocalization
+Thunk
+Children_playing
+Snake
+Chink,_clink
+Chirp,_tweet
+Boing
+Shuffle
+Pulse
+Punk_rock
+Crow
+Caw
+Static
+Clicking
+Snicker
+Whispering
+Pink_noise
+Crushing
+Wedding_music
+Crumpling,_crinkling
+Crackle
+Whoop
+Electric_toothbrush
+Train_wheels_squealing
+Yell
+Wind_chime
+Frying_(food)
+Christmas_music
+Fill_(with_liquid)
+Reverberation
+Beatboxing
+Harmonica
+Banjo
+Sliding_door
+Groan
+Bagpipes
+Spray
+Stir
+Acoustic_guitar
+Tap
+Chorus_effect
+Noise
+Crunch
+Biting
+Aircraft_engine
+Busy_signal
+Bang
+Techno
+Tuning_fork
+Tapping_(guitar_technique)
+Pig
+Maraca
+Vacuum_cleaner
+Mandolin
+Electronica
+Theme_music
+Yip
+A_capella
+Rustle
+Chatter
+Traditional_music
+Soul_music
+Rustling_leaves
+Afrobeat
+Hoot
+Slosh
+Roaring_cats_(lions,_tigers)
+Chopping_(food)
+Heavy_engine_(low_frequency)
+Sine_wave
+Speech_synthesizer
+Middle_Eastern_music
+Music_of_Latin_America
+Arrow
+Timpani
+Eruption
+Shofar
+Jingle_bell
+Humming
+Sanding
+Female_speech,_woman_speaking
+Gong
+Rain_on_surface
+Pant
+Dubstep
+Clip-clop
+Finger_snapping
+Blender
+Drum_and_bass
+Bouncing
+Vehicle_horn,_car_horn,_honking
+Slam
+Idling
+Rhythm_and_blues
+Race_car,_auto_racing
+Single-lens_reflex_camera
+Smash,_crash
+Purr
+Shatter
+Steelpan
+Whimper_(dog)
+Power_windows,_electric_windows
+Battle_cry
+Scary_music
+Hands
+Echo
+Truck
+Buzz
+Mechanical_fan
+Plop
+Run
+Gasp
+Psychedelic_rock
+Grunt
+Helicopter
+Dental_drill,_dentist's_drill
+Babbling
+Zing
+Oink
+Soundtrack_music
+Ambulance_(siren)
+Exciting_music
+Telephone
+Jingle_(music)
+Tubular_bells
+Burping,_eructation
+Baby_laughter
+Ping
+Bow-wow
+Foghorn
+Machine_gun
+Ukulele
+Telephone_bell_ringing
+Pulleys
+Gears
+Sigh
+Coin_(dropping)
+Music_of_Africa
+Scissors
+Inside,_public_space
+Trance_music
+Roll
+Thump,_thud
+Air_conditioning
+Ding-dong
+Ratchet,_pawl
+Hair_dryer
+Shout
+Ambient_music
+Music_for_children
+Toot
+Bathtub_(filling_or_washing)
+Slap,_smack
+Chuckle,_chortle
+Traffic_noise,_roadway_noise
+Bicycle
+Whimper
+Doorbell
+Wheeze
+Sailboat,_sailing_ship
+Cap_gun
+Wail,_moan
+Rock_and_roll
+Jingle,_tinkle
+Fire_engine,_fire_truck_(siren)
+Funk
+Lullaby
+Field_recording
+Skateboard
+Steam
+Rumble
+Medium_engine_(mid_frequency)
+Sound_effect
+Flamenco
+Shuffling_cards
+Subway,_metro,_underground
+Police_car_(siren)
+Folk_music
+Crying,_sobbing
+New-age_music
+Ice_cream_truck,_ice_cream_van
+Music_of_Bollywood
+Accelerating,_revving,_vroom
+Screaming
+Motorcycle
+Engine_starting
+Train_whistle
+Car_passing_by
+Bus
+Sneeze
+Train_horn
+Air_horn,_truck_horn
+Civil_defense_siren
+Car_alarm
+Reversing_beeps
+<blank>
+<unk>

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/RESULTS.md

@@ -0,0 +1,16 @@
+<!-- Generated by scripts/utils/show_cls_result.sh -->
+# RESULTS
+## Environments
+- date: `Fri Mar 21 05:05:28 CDT 2025`
+- python version: `3.9.18 | packaged by conda-forge | (main, Dec 23 2023, 17:20:25)  [GCC 12.3.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.6.0.dev20241210+cu124`
+- Git hash: `ee8dd3d5da745a2c08c2bd6518bc0ba41ba5b224`
+  - Commit date: `Thu Mar 20 16:45:17 2025 -0500`
+
+## cls_earbasei3
+|Split|mean_acc|mAP|mean_auc|n_labels|n_instances|
+|---|---|---|---|---|---|
+cls_eval|47.76|32.09|95.67|527.00|20123.00
+cls_val|45.63|36.62|94.72|527.00|2014.00
+

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/config.yaml

@@ -0,0 +1,731 @@
+config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/earbasei3/conf/ear_base/audioset20k.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/audioset20k/cls_earbasei3
+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: 160
+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: audioset20k.earbasei3
+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: 80
+valid_batch_size: 1200
+batch_bins: 1000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/speech_shape
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/label_shape
+valid_shape_file:
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/speech_shape
+- /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/label_shape
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 160000
+- 600
+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/audioset20k/train/wav.scp
+    - speech
+    - sound
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/train/text
+    - label
+    - text
+valid_data_path_and_name_and_type:
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/val/wav.scp
+    - speech
+    - sound
+-   - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/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: 500
+    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/audioset20k/cls_earbasei3
+token_list:
+- Music
+- Speech
+- Vehicle
+- Inside,_small_room
+- Animal
+- Musical_instrument
+- Singing
+- Domestic_animals,_pets
+- Guitar
+- Plucked_string_instrument
+- Water
+- Car
+- Dog
+- Percussion
+- Wind_instrument,_woodwind_instrument
+- Outside,_urban_or_manmade
+- Outside,_rural_or_natural
+- Boat,_Water_vehicle
+- Brass_instrument
+- Fowl
+- Drum
+- Siren
+- Engine
+- Bird
+- Insect
+- Gunshot,_gunfire
+- Wood
+- Rail_transport
+- Train
+- Wind
+- Inside,_large_room_or_hall
+- Railroad_car,_train_wagon
+- Child_speech,_kid_speaking
+- Crowd
+- Rub
+- Keyboard_(musical)
+- Wind_noise_(microphone)
+- Pizzicato
+- Emergency_vehicle
+- Bird_vocalization,_bird_call,_bird_song
+- Livestock,_farm_animals,_working_animals
+- Cat
+- Organ
+- Fly,_housefly
+- Mechanisms
+- Bowed_string_instrument
+- Rain
+- Laughter
+- Aircraft
+- Electronic_music
+- Effects_unit
+- Hum
+- Tools
+- Drum_kit
+- Snare_drum
+- Hiss
+- Piano
+- Water_tap,_faucet
+- Rimshot
+- Bass_drum
+- Chicken,_rooster
+- Marimba,_xylophone
+- Horse
+- Song
+- Quack
+- Power_tool
+- Heart_sounds,_heartbeat
+- Goose
+- Hammond_organ
+- Rock_music
+- Ocean
+- Mains_hum
+- Thunder
+- Chime
+- Electronic_dance_music
+- Typing
+- Sink_(filling_or_washing)
+- Raindrop
+- Cello
+- Electric_guitar
+- Cheering
+- Church_bell
+- Christian_music
+- Drum_roll
+- Trombone
+- Glockenspiel
+- Trumpet
+- Cymbal
+- Tabla
+- Clickety-clack
+- Cricket
+- Steam_whistle
+- Explosion
+- Saxophone
+- Thunderstorm
+- Pop_music
+- Zither
+- Applause
+- Choir
+- Whack,_thwack
+- Clarinet
+- Camera
+- Electric_piano
+- Independent_music
+- Fire
+- Frog
+- Jet_engine
+- Music_of_Asia
+- Ding
+- Waves,_surf
+- Cattle,_bovinae
+- Turkey
+- Television
+- Coo
+- Scratching_(performance_technique)
+- Flute
+- Liquid
+- Harp
+- Progressive_rock
+- Happy_music
+- Steel_guitar,_slide_guitar
+- Whoosh,_swoosh,_swish
+- Boom
+- Breathing
+- Electronic_organ
+- Environmental_noise
+- Distortion
+- Alarm_clock
+- Fixed-wing_aircraft,_airplane
+- Violin,_fiddle
+- Whistling
+- Accordion
+- Disco
+- Pump_(liquid)
+- Waterfall
+- Beep,_bleep
+- Blues
+- Grunge
+- Hip_hop_music
+- Whistle
+- Fusillade
+- Splash,_splatter
+- Gush
+- Toothbrush
+- Knock
+- Gargling
+- Snoring
+- Hammer
+- Gobble
+- Walk,_footsteps
+- Jackhammer
+- Filing_(rasp)
+- Snort
+- Narration,_monologue
+- Tire_squeal
+- Fire_alarm
+- Squeal
+- Meow
+- Caterwaul
+- Cutlery,_silverware
+- Mantra
+- Opera
+- Classical_music
+- Theremin
+- Burst,_pop
+- Drip
+- Tick
+- Children_shouting
+- Creak
+- Hiccup
+- Pigeon,_dove
+- Bicycle_bell
+- Baby_cry,_infant_cry
+- Duck
+- Fireworks
+- Tambourine
+- Rodents,_rats,_mice
+- Buzzer
+- Splinter
+- Writing
+- Goat
+- Sheep
+- Heavy_metal
+- Ska
+- Neigh,_whinny
+- Sizzle
+- Rowboat,_canoe,_kayak
+- Wood_block
+- Clang
+- Door
+- Female_singing
+- Stream
+- Chant
+- Vocal_music
+- Yodeling
+- Bee,_wasp,_etc.
+- Air_brake
+- Whir
+- Bird_flight,_flapping_wings
+- French_horn
+- Telephone_dialing,_DTMF
+- Squeak
+- Sitar
+- Smoke_detector,_smoke_alarm
+- Tick-tock
+- Gurgling
+- Bellow
+- Harmonic
+- Male_singing
+- Giggle
+- Bark
+- Vibration
+- Drill
+- Skidding
+- Scratch
+- Drawer_open_or_close
+- Chop
+- Drum_machine
+- Squish
+- Toilet_flush
+- Fart
+- Basketball_bounce
+- Electronic_tuner
+- Singing_bowl
+- Squawk
+- Conversation
+- Reggae
+- Funny_music
+- Scrape
+- Sewing_machine
+- Tender_music
+- Swing_music
+- Dishes,_pots,_and_pans
+- Sampler
+- Synthesizer
+- Clapping
+- Hubbub,_speech_noise,_speech_babble
+- Engine_knocking
+- Canidae,_dogs,_wolves
+- Chainsaw
+- Pour
+- Croak
+- Chewing,_mastication
+- Cowbell
+- Propeller,_airscrew
+- Didgeridoo
+- Ringtone
+- Rattle_(instrument)
+- Artillery_fire
+- Cash_register
+- Crack
+- Growling
+- Mosquito
+- Carnatic_music
+- Honk
+- Howl
+- Cacophony
+- Gospel_music
+- Firecracker
+- Strum
+- Motorboat,_speedboat
+- Clock
+- Dance_music
+- Microwave_oven
+- Country
+- Bluegrass
+- Rattle
+- Mallet_percussion
+- Computer_keyboard
+- Bass_guitar
+- Electric_shaver,_electric_razor
+- Sawing
+- Owl
+- Whip
+- White_noise
+- Chirp_tone
+- Boiling
+- Ship
+- Mouse
+- Breaking
+- Silence
+- Throat_clearing
+- Bleat
+- Salsa_music
+- Patter
+- Vibraphone
+- Flap
+- Typewriter
+- Change_ringing_(campanology)
+- Trickle,_dribble
+- Video_game_music
+- Glass
+- Dial_tone
+- Radio
+- Bell
+- Moo
+- Heart_murmur
+- Clatter
+- Sniff
+- Double_bass
+- Background_music
+- Lawn_mower
+- Printer
+- House_music
+- Tearing
+- Angry_music
+- Male_speech,_man_speaking
+- Wild_animals
+- Cupboard_open_or_close
+- Harpsichord
+- Light_engine_(high_frequency)
+- Child_singing
+- Zipper_(clothing)
+- Jazz
+- Belly_laugh
+- Roar
+- Motor_vehicle_(road)
+- Crowing,_cock-a-doodle-doo
+- Cluck
+- Sad_music
+- Hi-hat
+- Cough
+- Stomach_rumble
+- Alarm
+- String_section
+- Sonar
+- Keys_jangling
+- Synthetic_singing
+- Rapping
+- Sidetone
+- Orchestra
+- Throbbing
+- Whale_vocalization
+- Thunk
+- Children_playing
+- Snake
+- Chink,_clink
+- Chirp,_tweet
+- Boing
+- Shuffle
+- Pulse
+- Punk_rock
+- Crow
+- Caw
+- Static
+- Clicking
+- Snicker
+- Whispering
+- Pink_noise
+- Crushing
+- Wedding_music
+- Crumpling,_crinkling
+- Crackle
+- Whoop
+- Electric_toothbrush
+- Train_wheels_squealing
+- Yell
+- Wind_chime
+- Frying_(food)
+- Christmas_music
+- Fill_(with_liquid)
+- Reverberation
+- Beatboxing
+- Harmonica
+- Banjo
+- Sliding_door
+- Groan
+- Bagpipes
+- Spray
+- Stir
+- Acoustic_guitar
+- Tap
+- Chorus_effect
+- Noise
+- Crunch
+- Biting
+- Aircraft_engine
+- Busy_signal
+- Bang
+- Techno
+- Tuning_fork
+- Tapping_(guitar_technique)
+- Pig
+- Maraca
+- Vacuum_cleaner
+- Mandolin
+- Electronica
+- Theme_music
+- Yip
+- A_capella
+- Rustle
+- Chatter
+- Traditional_music
+- Soul_music
+- Rustling_leaves
+- Afrobeat
+- Hoot
+- Slosh
+- Roaring_cats_(lions,_tigers)
+- Chopping_(food)
+- Heavy_engine_(low_frequency)
+- Sine_wave
+- Speech_synthesizer
+- Middle_Eastern_music
+- Music_of_Latin_America
+- Arrow
+- Timpani
+- Eruption
+- Shofar
+- Jingle_bell
+- Humming
+- Sanding
+- Female_speech,_woman_speaking
+- Gong
+- Rain_on_surface
+- Pant
+- Dubstep
+- Clip-clop
+- Finger_snapping
+- Blender
+- Drum_and_bass
+- Bouncing
+- Vehicle_horn,_car_horn,_honking
+- Slam
+- Idling
+- Rhythm_and_blues
+- Race_car,_auto_racing
+- Single-lens_reflex_camera
+- Smash,_crash
+- Purr
+- Shatter
+- Steelpan
+- Whimper_(dog)
+- Power_windows,_electric_windows
+- Battle_cry
+- Scary_music
+- Hands
+- Echo
+- Truck
+- Buzz
+- Mechanical_fan
+- Plop
+- Run
+- Gasp
+- Psychedelic_rock
+- Grunt
+- Helicopter
+- Dental_drill,_dentist's_drill
+- Babbling
+- Zing
+- Oink
+- Soundtrack_music
+- Ambulance_(siren)
+- Exciting_music
+- Telephone
+- Jingle_(music)
+- Tubular_bells
+- Burping,_eructation
+- Baby_laughter
+- Ping
+- Bow-wow
+- Foghorn
+- Machine_gun
+- Ukulele
+- Telephone_bell_ringing
+- Pulleys
+- Gears
+- Sigh
+- Coin_(dropping)
+- Music_of_Africa
+- Scissors
+- Inside,_public_space
+- Trance_music
+- Roll
+- Thump,_thud
+- Air_conditioning
+- Ding-dong
+- Ratchet,_pawl
+- Hair_dryer
+- Shout
+- Ambient_music
+- Music_for_children
+- Toot
+- Bathtub_(filling_or_washing)
+- Slap,_smack
+- Chuckle,_chortle
+- Traffic_noise,_roadway_noise
+- Bicycle
+- Whimper
+- Doorbell
+- Wheeze
+- Sailboat,_sailing_ship
+- Cap_gun
+- Wail,_moan
+- Rock_and_roll
+- Jingle,_tinkle
+- Fire_engine,_fire_truck_(siren)
+- Funk
+- Lullaby
+- Field_recording
+- Skateboard
+- Steam
+- Rumble
+- Medium_engine_(mid_frequency)
+- Sound_effect
+- Flamenco
+- Shuffling_cards
+- Subway,_metro,_underground
+- Police_car_(siren)
+- Folk_music
+- Crying,_sobbing
+- New-age_music
+- Ice_cream_truck,_ice_cream_van
+- Music_of_Bollywood
+- Accelerating,_revving,_vroom
+- Screaming
+- Motorcycle
+- Engine_starting
+- Train_whistle
+- Car_passing_by
+- Bus
+- Sneeze
+- Train_horn
+- Air_horn,_truck_horn
+- Civil_defense_siren
+- Car_alarm
+- Reversing_beeps
+- <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/7Msounds/exp/beats_iter2_base2.tune_lr5e-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: 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: 0.8
+    lsm_weight: 0.0
+    log_epoch_metrics: true
+user_callbacks:
+- mAP_logging
+required:
+- output_dir
+- token_list
+task: cls

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/lightning_logs/version_0/events.out.tfevents.1742492588.gh130.hsn.cm.delta.internal.ncsa.edu.3586759.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca3b0dad08cf2f8f38bfd982441259e80d8b95377c492704e465a2e08c4ad2c
+size 372371

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1,208 @@
+args: !!python/object:argparse.Namespace
+  accum_grad: 1
+  adapter: lora
+  adapter_conf: {}
+  allow_multi_rates: false
+  allow_variable_data_keys: false
+  batch_bins: 1000000
+  batch_size: 80
+  batch_type: folded
+  best_model_criterion:
+  - - valid
+    - epoch_mAP
+    - max
+  category_sample_size: 10
+  chunk_default_fs: null
+  chunk_discard_short_samples: true
+  chunk_excluded_key_prefixes: []
+  chunk_length: 500
+  chunk_max_abs_length: null
+  chunk_shift_ratio: 0.5
+  collect_stats: false
+  config: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/earbasei3/conf/ear_base/audioset20k.yaml
+  create_graph_in_tensorboard: false
+  cudnn_benchmark: false
+  cudnn_deterministic: true
+  cudnn_enabled: true
+  ddp_comm_hook: null
+  decoder: linear
+  decoder_conf: {}
+  deepspeed_config: null
+  detect_anomaly: false
+  dist_backend: nccl
+  dist_init_method: env://
+  dist_launcher: null
+  dist_master_addr: null
+  dist_master_port: null
+  dist_rank: null
+  dist_world_size: null
+  drop_last_iter: false
+  dry_run: false
+  early_stopping_criterion: !!python/tuple
+  - valid
+  - loss
+  - min
+  embedding_fusion: null
+  embedding_fusion_conf: {}
+  encoder: beats
+  encoder_conf:
+    beats_ckpt_path: /work/nvme/bbjs/sbharadwaj/7Msounds/exp/beats_iter2_base2.tune_lr5e-4_warmup40000_bins1600000_totalsteps400000/epoch_latest.pt
+    beats_config:
+      dropout: 0.0
+      encoder_layerdrop: 0.1
+      layer_wise_gradient_decay_ratio: 0.3
+    roll_augment: true
+    roll_interval: 1
+    specaug_config:
+      apply_freq_mask: false
+      apply_time_mask: true
+      apply_time_warp: true
+      num_time_mask: 1
+      time_mask_width_ratio_range:
+      - 0
+      - 0.06
+    use_weighted_representation: false
+  exclude_weight_decay: false
+  exclude_weight_decay_conf: {}
+  fold_length:
+  - 160000
+  - 600
+  freeze_param: []
+  frontend: null
+  frontend_conf:
+    fs: 16k
+  grad_clip: 1
+  grad_clip_type: 2.0
+  grad_noise: false
+  gradient_as_bucket_view: true
+  ignore_init_mismatch: false
+  init: xavier_normal
+  init_param: []
+  input_size: 1
+  iterator_type: sequence
+  keep_nbest_models: 1
+  lightning_conf:
+    best_model_criterion:
+    - - valid/epoch_mAP
+      - max
+      - 1
+    default_root_dir: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3
+    devices: 1
+    log_every_n_steps: 250
+    max_epochs: 500
+    num_nodes: 1
+    strategy: ddp
+    strategy_conf:
+      find_unused_parameters: true
+  local_rank: null
+  log_interval: null
+  log_level: INFO
+  max_cache_fd: 32
+  max_cache_size: 0.0
+  max_epoch: 160
+  model: espnet
+  model_conf:
+    classification_type: multi-label
+    log_epoch_metrics: true
+    lsm_weight: 0.0
+    mixup_probability: 0.8
+  multi_task_dataset: false
+  multiple_iterator: false
+  multiprocessing_distributed: false
+  nbest_averaging_interval: 0
+  ngpu: 0
+  no_forward_run: false
+  normalize: null
+  normalize_conf: {}
+  num_att_plot: 0
+  num_cache_chunks: 1024
+  num_iters_per_epoch: null
+  num_workers: 2
+  optim: adamw
+  optim_conf:
+    betas:
+    - 0.9
+    - 0.98
+    lr: 3.0e-05
+    weight_decay: 0.01
+  output_dir: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3
+  patience: null
+  preencoder: null
+  preencoder_conf: {}
+  pretrain_path: null
+  print_config: false
+  required:
+  - output_dir
+  - token_list
+  resume: true
+  save_strategy: all
+  scheduler: cosineannealingwarmuprestarts
+  scheduler_conf:
+    first_cycle_steps: 95000
+    max_lr: 3.0e-05
+    min_lr: 5.0e-06
+    warmup_steps: 8000
+  seed: 0
+  sharded_ddp: false
+  shuffle_within_batch: false
+  sort_batch: descending
+  sort_in_batch: descending
+  specaug: null
+  specaug_conf: {}
+  task: cls
+  text_bpemodel: null
+  text_encoder: null
+  text_encoder_conf: {}
+  text_token_list: null
+  token_list: /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/data/audioset20k/token_list
+  train_data_path_and_name_and_type:
+  - !!python/tuple
+    - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/train/wav.scp
+    - speech
+    - sound
+  - !!python/tuple
+    - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/train/text
+    - label
+    - text
+  train_dtype: float32
+  train_shape_file:
+  - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/speech_shape
+  - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/train/label_shape
+  unused_parameters: true
+  use_adapter: false
+  use_amp: false
+  use_deepspeed: false
+  use_matplotlib: true
+  use_preprocessor: true
+  use_tensorboard: true
+  use_tf32: false
+  use_wandb: true
+  user_callbacks:
+  - mAP_logging
+  utt2weight_file: null
+  val_scheduler_criterion: !!python/tuple
+  - valid
+  - loss
+  valid_batch_bins: null
+  valid_batch_size: 1200
+  valid_batch_type: null
+  valid_data_path_and_name_and_type:
+  - !!python/tuple
+    - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/val/wav.scp
+    - speech
+    - sound
+  - !!python/tuple
+    - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/dump/audioset20k/val/text
+    - label
+    - text
+  valid_iterator_type: null
+  valid_max_cache_size: null
+  valid_shape_file:
+  - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/speech_shape
+  - /work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_stats_16k/valid/label_shape
+  wandb_entity: shikhar
+  wandb_id: null
+  wandb_model_log_interval: -1
+  wandb_name: audioset20k.earbasei3
+  wandb_project: audioverse
+  write_collected_feats: false

work/nvme/bbjs/sbharadwaj/espnet/egs2/audioverse/v1/exp/audioset20k/cls_earbasei3/valid.epoch_mAP.ave_1best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09cbf19b179115d8b0af485d8efe9bf889147393cc0a8ad2fa2d0506237147f2
+size 363126298