add model

exp/asr_train_asr_conformer6_n_fft400_hop_length160_raw_bn_char/config.yaml

@@ -0,0 +1,274 @@
+config: conf/tuning/train_asr_conformer6_n_fft400_hop_length160.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_conformer6_n_fft400_hop_length160_raw_bn_char
+ngpu: 1
+seed: 0
+num_workers: 1
+num_att_plot: 3
+dist_backend: nccl
+dist_init_method: env://
+dist_world_size: 2
+dist_rank: 0
+local_rank: 0
+dist_master_addr: localhost
+dist_master_port: 41903
+dist_launcher: null
+multiprocessing_distributed: true
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 35
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 3
+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: false
+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
+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: 4000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_bn_char/train/speech_shape
+- exp/asr_stats_raw_bn_char/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_bn_char/valid/speech_shape
+- exp/asr_stats_raw_bn_char/valid/text_shape.char
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+train_data_path_and_name_and_type:
+-   - dump/raw/bn/train/wav.scp
+    - speech
+    - sound
+-   - dump/raw/bn/train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/bn/dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/bn/dev/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.0015
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- ा
+- े
+- क
+- र
+- ल
+- स
+- न
+- म
+- त
+- ी
+- ि
+- ह
+- ब
+- ्
+- प
+- व
+- ो
+- ज
+- ं
+- ख
+- द
+- य
+- ग
+- ट
+- ई
+- ु
+- इ
+- च
+- अ
+- आ
+- उ
+- ू
+- भ
+- ए
+- ै
+- फ
+- ध
+- ड
+- श
+- ड़
+- ौ
+- .
+- ण
+- छ
+- ष
+- थ
+- ढ़
+- ओ
+- ठ
+- घ
+- ृ
+- ॉ
+- ऑ
+- ँ
+- ऋ
+- औ
+- ढ
+- ऊ
+- ज़
+- झ
+- फ़
+- ऐ
+- ऽ
+- ञ
+- ़
+- ख़
+- क़
+- ॅ
+- ः
+- ऱ
+- <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
+joint_net_conf: null
+use_preprocessor: true
+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
+frontend: default
+frontend_conf:
+    n_fft: 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
+    - 30
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_range:
+    - 0
+    - 40
+    num_time_mask: 2
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw_bn_char/train/feats_stats.npz
+model: espnet
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+preencoder: null
+preencoder_conf: {}
+encoder: conformer
+encoder_conf:
+    output_size: 512
+    attention_heads: 8
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    macaron_style: true
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_kernel: 31
+postencoder: null
+postencoder_conf: {}
+decoder: transformer
+decoder_conf:
+    attention_heads: 8
+    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
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202211'
+distributed: true

exp/asr_train_asr_conformer6_n_fft400_hop_length160_raw_bn_char/valid.acc.ave_3best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1a155c7b7184072d3feaeded51297450e5d830326dabf0b28b8cbec0a0491a
+size 434598181