myst_ogi_cmu_kids_aed_upsample

Usage

import librosa
from espnet2.bin.asr_inference import Speech2Text

speech2text = Speech2Text.from_pretrained(model_tag="espnet/myst_ogi_cmu_kids_aed_upsample")
# librosa resamples and mixes to one channel, so any file works; 16000 is
# what nearly every espnet recogniser is trained on - check this model's
# config if its audio is not 16 kHz
speech, rate = librosa.load("audio.wav", sr=16000, mono=True)
text, *_ = speech2text(speech)[0]
print(text)

ESPnet2 ASR model

espnet/myst_ogi_cmu_kids_aed_upsample

This model was trained by eric102004 using myst_ogi_cmu_kids 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 6f722aee1f9593572d5eddfd8cac7075b07cf9ca
pip install -e .
cd egs2/myst_ogi_cmu_kids/asr1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/myst_ogi_cmu_kids_aed_upsample

<!-- Generated by scripts/utils/show_asr_result.sh -->

RESULTS

Environments

• date: Wed Feb 19 19:12:32 CST 2025
• python version: 3.12.3 | packaged by Anaconda, Inc. | (main, May 6 2024, 19:46:43) [GCC 11.2.0]
• espnet version: espnet 202412
• pytorch version: pytorch 2.4.0
• Git hash: 6f722aee1f9593572d5eddfd8cac7075b07cf9ca
  • Commit date: Thu Feb 6 22:32:07 2025 -0600

exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/decode_asr_asr_model_valid.cer.ave_10best

WER

CER

TER

ASR config

<details><summary>expand</summary>

config: conf/tuning/train_asr_lr002.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_lr002_raw_en_char_dur05_filter_ba_h2l4
ngpu: 1
seed: 2022
num_workers: 4
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: null
dist_rank: null
local_rank: 0
dist_master_addr: null
dist_master_port: null
dist_launcher: null
multiprocessing_distributed: false
unused_parameters: false
sharded_ddp: false
use_deepspeed: false
deepspeed_config: null
static_graph: false
gradient_as_bucket_view: false
broadcast_buffers: true
bucket_cap_mb: 25
compress_gradients: false
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
    - cer
    - min
keep_nbest_models: 10
nbest_averaging_interval: 0
grad_clip: 5.0
grad_clip_type: 2.0
grad_noise: false
accum_grad: 4
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
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
train_shape_file:
- exp/asr_stats_raw_en_char_ba_h2l4/train/speech_shape
- exp/asr_stats_raw_en_char_ba_h2l4/train/text_shape.char
valid_shape_file:
- exp/asr_stats_raw_en_char_ba_h2l4/valid/speech_shape
- exp/asr_stats_raw_en_char_ba_h2l4/valid/text_shape.char
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
validate_each_iter_factory: true
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_no_special_ba_h2l4/raw/train/wav.scp
    - speech
    - sound
-   - dump_no_special_ba_h2l4/raw/train/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump_no_special_ba_h2l4/raw/dev/wav.scp
    - speech
    - sound
-   - dump_no_special_ba_h2l4/raw/dev/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
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 15000
token_list:
- <blank>
- <unk>
- <space>
- E
- T
- A
- O
- I
- N
- H
- S
- R
- L
- D
- U
- W
- M
- C
- G
- Y
- B
- P
- F
- K
- ''''
- V
- X
- J
- Z
- Q
- ','
- '-'
- <sos/eos>
init: null
input_size: null
ctc_conf:
    dropout_rate: 0.0
    ctc_type: builtin
    reduce: true
    ignore_nan_grad: null
    zero_infinity: true
    brctc_risk_strategy: exp
    brctc_group_strategy: end
    brctc_risk_factor: 0.0
joint_net_conf: null
use_preprocessor: true
use_lang_prompt: false
use_nlp_prompt: false
token_type: char
bpemodel: null
non_linguistic_symbols: null
cleaner: null
g2p: null
speech_volume_normalize: null
rir_scp: null
rir_apply_prob: 1.0
noise_scp: null
noise_apply_prob: 1.0
noise_db_range: '13_15'
short_noise_thres: 0.5
aux_ctc_tasks: []
frontend: default
frontend_conf:
    n_fft: 512
    win_length: 400
    hop_length: 160
    fs: 16k
specaug: specaug
specaug_conf:
    apply_time_warp: true
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 27
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_ratio_range:
    - 0.0
    - 0.05
    num_time_mask: 5
normalize: utterance_mvn
normalize_conf: {}
model: espnet
model_conf:
    ctc_weight: 0.3
    lsm_weight: 0.1
    length_normalized_loss: false
preencoder: null
preencoder_conf: {}
encoder: e_branchformer
encoder_conf:
    output_size: 256
    attention_heads: 4
    attention_layer_type: rel_selfattn
    pos_enc_layer_type: rel_pos
    rel_pos_type: latest
    cgmlp_linear_units: 1024
    cgmlp_conv_kernel: 31
    use_linear_after_conv: false
    gate_activation: identity
    num_blocks: 12
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.1
    input_layer: conv2d
    layer_drop_rate: 0.0
    linear_units: 1024
    positionwise_layer_type: linear
    use_ffn: true
    macaron_ffn: true
    merge_conv_kernel: 31
postencoder: null
postencoder_conf: {}
decoder: transformer
decoder_conf:
    attention_heads: 4
    linear_units: 2048
    num_blocks: 6
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    self_attention_dropout_rate: 0.1
    src_attention_dropout_rate: 0.1
    layer_drop_rate: 0.0
preprocessor: default
preprocessor_conf: {}
masker: null
masker_conf: {}
required:
- output_dir
- token_list
version: '202412'
distributed: false

</details>

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},
  url={http://dx.doi.org/10.21437/Interspeech.2018-1456}
}

or arXiv:

@misc{watanabe2018espnet,
  title={ESPnet: End-to-End Speech Processing Toolkit},
  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},
  year={2018},
  eprint={1804.00015},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}