ESPnet2 ASR model

espnet/ta_openslr127

This model was trained by Rishab Alagharu using ta_openslr127 recipe in espnet.

Demo: How to use in ESPnet2

Follow the ESPnet installation instructions if you haven't done that already.

cd espnet
git checkout 6c28df5d6c8eb82f312642eeeb65a2e94f614b65
pip install -e .
cd egs2/ta_openslr127/asr1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/ta_openslr127

RESULTS

Environments

• date: Wed Jun 10 07:16:47 CDT 2026
• python version: 3.10.20 (main, Mar 11 2026, 17:46:40) [GCC 14.3.0]
• espnet2 version: espnet2 202604
• pytorch version: pytorch 2.9.1+cu128
• Git hash: e02e6f79766aa12a13327af8b537543966613500
  • Commit date: Sun Jun 7 11:03:05 2026 -0400

exp/asr_train_asr_raw_ta_bpe1000_accum_grad1_sp

WER

CER

TER

exp/asr_train_asr_raw_ta_bpe1000_accum_grad1_sp/decode_asr_lm_lm_train_lm_ta_bpe1000_valid.loss.ave_asr_model_valid.acc.ave

WER

CER

TER

ASR config

config: conf/train_asr.yaml
print_config: false
log_level: INFO
drop_last_iter: false
dry_run: false
iterator_type: sequence
valid_iterator_type: null
output_dir: exp/asr_train_asr_raw_ta_bpe1000_accum_grad1_sp
ngpu: 1
seed: 2022
num_workers: 4
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: 4
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 60693
dist_launcher: null
multiprocessing_distributed: true
unused_parameters: false
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: 70
patience: null
val_scheduler_criterion:
- valid
- loss
early_stopping_criterion:
- valid
- loss
- min
best_model_criterion:
-   - valid
    - acc
    - max
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 1
no_forward_run: false
resume: true
train_dtype: float32
use_amp: true
log_interval: null
use_matplotlib: true
use_tensorboard: true
create_graph_in_tensorboard: false
use_wandb: false
wandb_project: null
wandb_id: null
wandb_entity: null
wandb_name: null
wandb_model_log_interval: -1
wandb_allow_val_change: true
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: 16000000
valid_batch_bins: null
category_sample_size: 10
upsampling_factor: 0.5
category_upsampling_factor: 0.5
dataset_upsampling_factor: 0.5
dataset_scaling_factor: 1.2
max_batch_size: null
min_batch_size: 1
train_shape_file:
- exp/asr_stats_raw_ta_bpe1000_sp/train/speech_shape
- exp/asr_stats_raw_ta_bpe1000_sp/train/text_shape.bpe
valid_shape_file:
- exp/asr_stats_raw_ta_bpe1000_sp/valid/speech_shape
- exp/asr_stats_raw_ta_bpe1000_sp/valid/text_shape.bpe
batch_type: numel
valid_batch_type: null
fold_length:
- 80000
- 150
sort_in_batch: descending
shuffle_within_batch: false
sort_batch: descending
multiple_iterator: false
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:
-   - dump/raw/train_ta_sp/wav.scp
    - speech
    - sound
-   - dump/raw/train_ta_sp/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/dev_ta/wav.scp
    - speech
    - sound
-   - dump/raw/dev_ta/text
    - text
    - 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: adam
optim_conf:
    lr: 0.002
    weight_decay: 1.0e-06
s