espnet/CI_mini_an4_training_asr_transformer

ESPnet3 asr model

Packed model bundle generated from egs3/mini_an4/asr.

Model

• Repository: ms180/CI_mini_an4_training_asr_transformer
• Recipe: egs3/mini_an4/asr
• Task: asr
• System: espnet3.systems.asr.task.ASRTask
• Creator: masao
• Created: 2026-05-11T19:28:10
• Branch: espnet3/publish_stage
• Commit: a0087239784f92b800ee9f12878af6cdb0e10c63 (a008723978)
• Worktree: dirty
• Origin: git@github.com:Masao-Someki/espnet.git

Usage

from espnet3.publication import InferenceModel

model = InferenceModel.from_pretrained("ms180/CI_mini_an4_training_asr_transformer", trust_user_code=True)
result = model(sample)

Packaging

• Bundle: model_pack
• Exp dir: ./exp/training_asr_transformer
• Strategy: copy experiment outputs; include extra recipe assets; register named artifact files; apply exclude filters

Results

dataset	CER	WER
test	213.43	100.0
valid	933.33	100.0

Training config

expand

num_device: 1
num_nodes: 1
task: espnet3.systems.asr.task.ASRTask
recipe_dir: .
data_dir: ./data
exp_tag: training_asr_transformer
exp_dir: ./exp/training_asr_transformer
stats_dir: ./exp/stats
dataset_dir: /path/to/your/dataset
create_dataset:
  func: src.creating_dataset.create_dataset
  dataset_dir: /path/to/your/dataset
  recipe_dir: .
dataset:
  _target_: espnet3.components.data.data_organizer.DataOrganizer
  recipe_dir: .
  train:
  - data_src_args:
      split: train
  valid:
  - data_src_args:
      split: valid
  test: null
  preprocessor:
    _target_: espnet2.train.preprocessor.CommonPreprocessor
    fs: 16000
    train: true
    data_aug_effects:
    - - 0.1
      - contrast
      - enhancement_amount: 75.0
    - - 0.1
      - highpass
      - cutoff_freq: 5000
        Q: 0.707
    - - 0.1
      - equalization
      - center_freq: 1000
        gain: 0
        Q: 0.707
    - - 0.1
      - - - 0.3
          - speed_perturb
          - factor: 0.9
        - - 0.3
          - speed_perturb
          - factor: 1.1
        - - 0.3
          - speed_perturb
          - factor: 1.3
    data_aug_num:
    - 1
    - 4
    data_aug_prob: 1.0
    token_type: bpe
    token_list: ./data/bpe_30/tokens.txt
    bpemodel: ./data/bpe_30/bpe.model
    _convert_: all
  _convert_: all
tokenizer:
  vocab_size: 30
  character_coverage: 1.0
  model_type: bpe
  save_path: ./data/bpe_30
  text_builder:
    func: src.tokenizer.gather_training_text
    manifest_path: ./data/manifest/train.tsv
model:
  vocab_size: 30
  token_list: ./data/bpe_30/tokens.txt
  encoder: transformer
  encoder_conf:
    output_size: 2
    attention_heads: 2
    linear_units: 2
    num_blocks: 2
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.0
    input_layer: conv1d2
    normalize_before: true
  decoder: transformer
  decoder_conf:
    attention_heads: 2
    linear_units: 2
    num_blocks: 2
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    self_attention_dropout_rate: 0.0
    src_attention_dropout_rate: 0.0
  model: espnet
  model_conf:
    ctc_weight: 0.3
    lsm_weight: 0.1
    length_normalized_loss: false
  frontend: default
  frontend_conf:
    n_fft: 512
    win_length: 400
    hop_length: 160
optimizer:
  _target_: torch.optim.Adam
  lr: 0.005
  weight_decay: 1.0e-06
  _convert_: all
scheduler:
  _target_: espnet2.schedulers.warmup_lr.WarmupLR
  warmup_steps: 100
  _convert_: all
scheduler_interval: step
scheduler_monitor: null
best_model_criterion:
- - valid/loss
  - 10
  - min
seed: null
init: xavier_uniform
parallel:
  env: local
  n_workers: 1
  options: {}
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: unsorted
        shape_files:
        - ./exp/stats/train/feats_shape
        batch_size: 2
        batch_bins: 4000000
      _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: unsorted
        shape_files:
        - ./exp/stats/valid/feats_shape
        batch_size: 2
        batch_bins: 4000000
      _convert_: all
trainer:
  accelerator: auto
  devices: 1
  num_nodes: 1
  accumulate_grad_batches: 1
  check_val_every_n_epoch: 1
  gradient_clip_val: 1.0
  log_every_n_steps: 100
  max_epochs: 1
  logger:
  - _target_: lightning.pytorch.loggers.TensorBoardLogger
    save_dir: ./exp/training_asr_transformer/tensorboard
    name: tb_logger
    _convert_: all
  strategy: auto
  limit_train_batches: 1
  limit_val_batches: 1
  reload_dataloaders_every_n_epochs: 1
  use_distributed_sampler: false
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}
}