espnet / meld_esp2_cls_wavlm_base_plus

huggingface.co
Total runs: 28
24-hour runs: 0
7-day runs: 12
30-day runs: 28
Model's Last Updated: September 21 2026

Introduction of meld_esp2_cls_wavlm_base_plus

Model Details of meld_esp2_cls_wavlm_base_plus

ESPnet3 esp2_cls model

Packed model bundle generated from egs3/meld/esp2_cls .

Model
  • Repository: espnet/meld_esp2_cls_wavlm_base_plus
  • Recipe: egs3/meld/esp2_cls
  • Corpus: meld
  • System: esp2_cls
  • Creator: ito
  • Created: 2026-09-21T17:54:46
  • Branch: recipe/meld-cls-espnet3
  • Git: e867b2d35e (dirty)
  • Origin: https://github.com/itoten/espnet.git
Model summary
  • Class: ClassificationModel
  • Total parameters: 95,801,220
  • Learnable parameters: 1,419,284 (1.5%)
  • Non-trainable parameters: 94,381,936
  • Parameter size: 383.2 MB
  • Buffers: 0 ( 0 bytes )
  • Modules: 308 total, 250 leaf
  • DType composition: torch.float32(100.0%)
Usage
from espnet3.publication import InferenceModel

model = InferenceModel.from_pretrained("espnet/meld_esp2_cls_wavlm_base_plus", trust_user_code=True)
result = model(sample)
Packaging
  • Bundle: model_pack
  • Exp dir: ./exp/train_cls_wavlm_transformer
  • Strategy: copy experiment outputs; include extra recipe assets; apply exclude filters
Results
dataset AUC MacroF1 UA WA mAP
test 68.83 24.32 24.63 51.61 27.31
valid 67.8 25.59 26.37 49.01 28.69
Training config
expand
num_device: 1
num_nodes: 1
task: espnet3.systems.esp2_cls.task.CLSTask
recipe_dir: .
data_dir: /mnt/ssd1tb/meld_espnet3
exp_tag: train_cls_wavlm_transformer
exp_dir: ./exp/train_cls_wavlm_transformer
stats_dir: ./exp/stats
create_dataset:
  recipe_dir: .
dataset:
  _target_: espnet3.components.data.data_organizer.DataOrganizer
  _recursive_: false
  recipe_dir: .
  train:
  - data_src_args:
      split: train
  valid:
  - data_src_args:
      split: valid
  test: null
  preprocessor:
    _target_: espnet2.train.preprocessor.CommonPreprocessor
    fs: 16000
    text_name: label
    token_type: word
    token_list: /mnt/ssd1tb/meld_espnet3/token_list
    _convert_: all
  _convert_: all
remove_long_short:
  min_wav_duration: 0.1
  max_wav_duration: 30
  splits:
  - train
  - valid
  save_path: /mnt/ssd1tb/meld_espnet3/manifest_filtered
  manifest_paths:
    train: /mnt/ssd1tb/meld_espnet3/manifest/train.tsv
    valid: /mnt/ssd1tb/meld_espnet3/manifest/valid.tsv
prepare_labels:
  save_path: /mnt/ssd1tb/meld_espnet3
  filename: token_list
  manifest_path: /mnt/ssd1tb/meld_espnet3/manifest_filtered/train.tsv
  add_symbol:
  - <unk>:-1
model:
  token_list: /mnt/ssd1tb/meld_espnet3/token_list
  frontend: s3prl
  frontend_conf:
    frontend_conf:
      upstream: wavlm_base_plus
    multilayer_feature: true
  freeze_param:
  - frontend.upstream
  normalize: utterance_mvn
  normalize_conf: {}
  encoder: transformer
  encoder_conf:
    output_size: 128
    attention_heads: 4
    linear_units: 1024
    num_blocks: 4
    dropout_rate: 0.4
    input_layer: linear
  decoder: linear
  model_conf:
    classification_type: multi-class
optimizer:
  _target_: torch.optim.Adam
  lr: 0.001
  weight_decay: 0
  _convert_: all
scheduler:
  _target_: espnet2.schedulers.warmup_lr.WarmupLR
  warmup_steps: 3180
  _convert_: all
scheduler_interval: step
scheduler_monitor: null
best_model_criterion:
- - valid/acc
  - 1
  - max
seed: 0
init: null
parallel:
  env: local
  n_workers: 8
  allow_overwrite_lock: false
dataloader:
  collate_fn:
    _target_: espnet2.train.collate_fn.CommonCollateFn
    int_pad_value: -1
    _convert_: all
  train:
    total_shards: 1
    dist_world_size: 1
    iter_factory:
      _target_: espnet2.iterators.sequence_iter_factory.SequenceIterFactory
      shuffle: true
      collate_fn:
        _target_: espnet2.train.collate_fn.CommonCollateFn
        int_pad_value: -1
        _convert_: all
      batches:
        type: folded
        shape_files:
        - ./exp/stats/train/feats_shape
        batch_size: 32
        batch_bins: 4000000
        fold_lengths:
        - 500
        sort_in_batch: descending
        sort_batch: descending
      _convert_: all
  valid:
    total_shards: 1
    dist_world_size: 1
    iter_factory:
      _target_: espnet2.iterators.sequence_iter_factory.SequenceIterFactory
      shuffle: false
      collate_fn:
        _target_: espnet2.train.collate_fn.CommonCollateFn
        int_pad_value: -1
        _convert_: all
      batches:
        type: folded
        shape_files:
        - ./exp/stats/valid/feats_shape
        batch_size: 32
        batch_bins: 4000000
        fold_lengths:
        - 500
        sort_in_batch: descending
        sort_batch: descending
      _convert_: all
trainer:
  accelerator: auto
  devices: 1
  num_nodes: 1
  accumulate_grad_batches: 1
  check_val_every_n_epoch: 1
  gradient_clip_val: 5.0
  log_every_n_steps: 100
  max_epochs: 30
  logger:
  - _target_: lightning.pytorch.loggers.TensorBoardLogger
    save_dir: ./exp/train_cls_wavlm_transformer/tensorboard
    name: tb_logger
    _convert_: all
  strategy: auto
  callbacks:
  - _target_: lightning.pytorch.callbacks.EarlyStopping
    monitor: valid/acc
    mode: max
    patience: 5
    _convert_: all
fit: {}
Citing ESPnet
@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}
}

Runs of espnet meld_esp2_cls_wavlm_base_plus on huggingface.co

28
Total runs
0
24-hour runs
7
3-day runs
12
7-day runs
28
30-day runs

More Information About meld_esp2_cls_wavlm_base_plus huggingface.co Model

meld_esp2_cls_wavlm_base_plus huggingface.co

meld_esp2_cls_wavlm_base_plus huggingface.co is an AI model on huggingface.co that provides meld_esp2_cls_wavlm_base_plus's model effect (), which can be used instantly with this espnet meld_esp2_cls_wavlm_base_plus model. huggingface.co supports a free trial of the meld_esp2_cls_wavlm_base_plus model, and also provides paid use of the meld_esp2_cls_wavlm_base_plus. Support call meld_esp2_cls_wavlm_base_plus model through api, including Node.js, Python, http.

meld_esp2_cls_wavlm_base_plus huggingface.co Url

https://huggingface.co/espnet/meld_esp2_cls_wavlm_base_plus

espnet meld_esp2_cls_wavlm_base_plus online free

meld_esp2_cls_wavlm_base_plus huggingface.co is an online trial and call api platform, which integrates meld_esp2_cls_wavlm_base_plus's modeling effects, including api services, and provides a free online trial of meld_esp2_cls_wavlm_base_plus, you can try meld_esp2_cls_wavlm_base_plus online for free by clicking the link below.

espnet meld_esp2_cls_wavlm_base_plus online free url in huggingface.co:

https://huggingface.co/espnet/meld_esp2_cls_wavlm_base_plus

meld_esp2_cls_wavlm_base_plus install

meld_esp2_cls_wavlm_base_plus is an open source model from GitHub that offers a free installation service, and any user can find meld_esp2_cls_wavlm_base_plus on GitHub to install. At the same time, huggingface.co provides the effect of meld_esp2_cls_wavlm_base_plus install, users can directly use meld_esp2_cls_wavlm_base_plus installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

meld_esp2_cls_wavlm_base_plus install url in huggingface.co:

https://huggingface.co/espnet/meld_esp2_cls_wavlm_base_plus

Url of meld_esp2_cls_wavlm_base_plus

meld_esp2_cls_wavlm_base_plus huggingface.co Url

Provider of meld_esp2_cls_wavlm_base_plus huggingface.co

espnet
ORGANIZATIONS

Other API from espnet

huggingface.co

Total runs: 11.1K
Run Growth: 2.5K
Growth Rate: 22.57%
Updated:October 11 2026
huggingface.co

Total runs: 4.7K
Run Growth: 1.1K
Growth Rate: 24.06%
Updated:September 18 2026
huggingface.co

Total runs: 209
Run Growth: 118
Growth Rate: 56.46%
Updated:January 22 2026
huggingface.co

Total runs: 161
Run Growth: 111
Growth Rate: 68.94%
Updated:September 20 2026
huggingface.co

Total runs: 116
Run Growth: 63
Growth Rate: 54.31%
Updated:October 11 2026
huggingface.co

Total runs: 93
Run Growth: 50
Growth Rate: 53.76%
Updated:June 17 2025
huggingface.co

Total runs: 32
Run Growth: 27
Growth Rate: 84.38%
Updated:October 11 2026
huggingface.co

Total runs: 22
Run Growth: 19
Growth Rate: 86.36%
Updated:August 26 2024
huggingface.co

Total runs: 20
Run Growth: 16
Growth Rate: 80.00%
Updated:May 03 2025
huggingface.co

Total runs: 19
Run Growth: 17
Growth Rate: 89.47%
Updated:September 20 2026