cmusic_dev

ESPnet2 ASR model

espnet/cmusic_dev

This model was trained by William Chen using librispeech 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 2d8caa9a5975195fbd59c6001b0e3e80d7aaff6a
pip install -e .
cd egs2/librispeech/asr1
./run.sh --skip_data_prep false --skip_train true --download_model espnet/cmusic_dev

ASR config

config: conf/train_asr_transformer.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_transformer_raw_en_word
ngpu: 1
seed: 0
num_workers: 4
num_att_plot: 0
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
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: 500
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: 100.0
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
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: 32000000
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_en_word/train/speech_shape
- exp/asr_stats_raw_en_word/train/text_shape.word
valid_shape_file:
- exp/asr_stats_raw_en_word/valid/speech_shape
- exp/asr_stats_raw_en_word/valid/text_shape.word
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/maestro_train_onsets/wav.scp
    - speech
    - sound
-   - dump/raw/maestro_train_onsets/text
    - text
    - text
valid_data_path_and_name_and_type:
-   - dump/raw/maestro_dev_onsets/wav.scp
    - speech
    - sound
-   - dump/raw/maestro_dev_onsets/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: 2.5e-05
scheduler: warmuplr
scheduler_conf:
    warmup_steps: 5000
token_list:
-
-
- AMT_MULTIINS_ONSETS
- AMT_ONSETS
- NOTE_ON_021
- NOTE_ON_022
- NOTE_ON_023
- NOTE_ON_024
- NOTE_ON_025
- NOTE_ON_026
- NOTE_ON_027
- NOTE_ON_028
- NOTE_ON_029
- NOTE_ON_030
- NOTE_ON_031
- NOTE_ON_032
- NOTE_ON_033
- NOTE_ON_034
- NOTE_ON_035
- NOTE_ON_036
- NOTE_ON_037
- NOTE_ON_038
- NOTE_ON_039
- NOTE_ON_040
- NOTE_ON_041
- NOTE_ON_042
- NOTE_ON_043
- NOTE_ON_044
- NOTE_ON_045
- NOTE_ON_046
- NOTE_ON_047
- NOTE_ON_048
- NOTE_ON_049
- NOTE_ON_050
- NOTE_ON_051
- NOTE_ON_052
- NOTE_ON_053
- NOTE_ON_054
- NOTE_ON_055
- NOTE_ON_056
- NOTE_ON_057
- NOTE_ON_058
- NOTE_ON_059
- NOTE_ON_060
- NOTE_ON_061
- NOTE_ON_062
- NOTE_ON_063
- NOTE_ON_064
- NOTE_ON_065
- NOTE_ON_066
- NOTE_ON_067
- NOTE_ON_068
- NOTE_ON_069
- NOTE_ON_070
- NOTE_ON_071
- NOTE_ON_072
- NOTE_ON_073
- NOTE_ON_074
- NOTE_ON_075
- NOTE_ON_076
- NOTE_ON_077
- NOTE_ON_078
- NOTE_ON_079
- NOTE_ON_080
- NOTE_ON_081
- NOTE_ON_082
- NOTE_ON_083
- NOTE_ON_084
- NOTE_ON_085
- NOTE_ON_086
- NOTE_ON_087
- NOTE_ON_088
- NOTE_ON_089
- NOTE_ON_090
- NOTE_ON_091
- NOTE_ON_092
- NOTE_ON_093
- NOTE_ON_094
- NOTE_ON_095
- NOTE_ON_096
- NOTE_ON_097
- NOTE_ON_098
- NOTE_ON_099
- NOTE_ON_100
- NOTE_ON_101
- NOTE_ON_102
- NOTE_ON_103
- NOTE_ON_104
- NOTE_ON_105
- NOTE_ON_106
- NOTE_ON_107
- NOTE_ON_108
- NOTE_ON_INS_000_PITCH_021
- NOTE_ON_INS_000_PITCH_022
- NOTE_ON_INS_000_PITCH_023
- NOTE_ON_INS_000_PITCH_024
- NOTE_ON_INS_000_PITCH_025
- NOTE_ON_INS_000_PITCH_026
- NOTE_ON_INS_000_PITCH_027
- NOTE_ON_INS_000_PITCH_028
- NOTE_ON_INS_000_PITCH_029
- NOTE_ON_INS_000_PITCH_030
- NOTE_ON_INS_000_PITCH_031
- NOTE_ON_INS_000_PITCH_032
- NOTE_ON_INS_000_PITCH_033
- NOTE_ON_INS_000_PITCH_034
- NOTE_ON_INS_000_PITCH_035
- NOTE_ON_INS_000_PITCH_036
- NOTE_ON_INS_000_PITCH_037
- NOTE_ON_INS_000_PITCH_038
- NOTE_ON_INS_000_PITCH_039
- NOTE_ON_INS_000_PITCH_040
- NOTE_ON_INS_000_PITCH_041
- NOTE_ON_INS_000_PITCH_042
- NOTE_ON_INS_000_PITCH_043
- NOTE_ON_INS_000_PITCH_044
- NOTE_ON_INS_000_PITCH_045
- NOTE_ON_INS_000_PITCH_046
- NOTE_ON_INS_000_PITCH_047
- NOTE_ON_INS_000_PITCH_048
- NOTE_ON_INS_000_PITCH_049
- NOTE_ON_INS_000_PITCH_050
- NOTE_ON_INS_000_PITCH_051
- NOTE_ON_INS_000_PITCH_052
- NOTE_ON_INS_000_PITCH_053
- NOTE_ON_INS_000_PITCH_054
- NOTE_ON_INS_000_PITCH_055
- NOTE_ON_INS_000_PITCH_056
- NOTE_ON_INS_000_PITCH_057
- NOTE_ON_INS_000_PITCH_058
- NOTE_ON_INS_000_PITCH_059
- NOTE_ON_INS_000_PITCH_060
- NOTE_ON_INS_000_PITCH_061
- NOTE_ON_INS_000_PITCH_062
- NOTE_ON_INS_