| config: conf/train_asr_transformer.yaml | |
| print_config: false | |
| log_level: INFO | |
| dry_run: false | |
| iterator_type: sequence | |
| output_dir: exp/asr_train_asr_transformer_raw_quy_bpe100_sp | |
| ngpu: 1 | |
| seed: 0 | |
| num_workers: 1 | |
| 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 | |
| cudnn_enabled: true | |
| cudnn_benchmark: false | |
| cudnn_deterministic: true | |
| collect_stats: false | |
| write_collected_feats: false | |
| max_epoch: 15 | |
| patience: null | |
| val_scheduler_criterion: | |
| - valid | |
| - loss | |
| early_stopping_criterion: | |
| - valid | |
| - loss | |
| - min | |
| best_model_criterion: | |
| - - valid | |
| - cer_ctc | |
| - min | |
| keep_nbest_models: 1 | |
| 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 | |
| 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: | |
| - frontend.upstream.model.feature_extractor | |
| - frontend.upstream.model.encoder.layers.0 | |
| - frontend.upstream.model.encoder.layers.1 | |
| - frontend.upstream.model.encoder.layers.2 | |
| - frontend.upstream.model.encoder.layers.3 | |
| - frontend.upstream.model.encoder.layers.4 | |
| - frontend.upstream.model.encoder.layers.5 | |
| - frontend.upstream.model.encoder.layers.6 | |
| - frontend.upstream.model.encoder.layers.7 | |
| - frontend.upstream.model.encoder.layers.8 | |
| - frontend.upstream.model.encoder.layers.9 | |
| - frontend.upstream.model.encoder.layers.10 | |
| - frontend.upstream.model.encoder.layers.11 | |
| - frontend.upstream.model.encoder.layers.12 | |
| - frontend.upstream.model.encoder.layers.13 | |
| - frontend.upstream.model.encoder.layers.14 | |
| - frontend.upstream.model.encoder.layers.15 | |
| - frontend.upstream.model.encoder.layers.16 | |
| - frontend.upstream.model.encoder.layers.17 | |
| - frontend.upstream.model.encoder.layers.18 | |
| - frontend.upstream.model.encoder.layers.19 | |
| - frontend.upstream.model.encoder.layers.20 | |
| - frontend.upstream.model.encoder.layers.21 | |
| num_iters_per_epoch: null | |
| batch_size: 20 | |
| valid_batch_size: null | |
| batch_bins: 200000 | |
| valid_batch_bins: null | |
| train_shape_file: | |
| - exp/asr_stats_raw_quy_bpe100_sp/train/speech_shape | |
| - exp/asr_stats_raw_quy_bpe100_sp/train/text_shape.bpe | |
| valid_shape_file: | |
| - exp/asr_stats_raw_quy_bpe100_sp/valid/speech_shape | |
| - exp/asr_stats_raw_quy_bpe100_sp/valid/text_shape.bpe | |
| 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/train_quy_sp/wav.scp | |
| - speech | |
| - sound | |
| - - dump/raw/train_quy_sp/text | |
| - text | |
| - text | |
| valid_data_path_and_name_and_type: | |
| - - dump/raw/dev_quy/wav.scp | |
| - speech | |
| - sound | |
| - - dump/raw/dev_quy/text | |
| - text | |
| - text | |
| allow_variable_data_keys: false | |
| max_cache_size: 0.0 | |
| max_cache_fd: 32 | |
| valid_max_cache_size: null | |
| optim: adamw | |
| optim_conf: | |
| lr: 0.0001 | |
| scheduler: warmuplr | |
| scheduler_conf: | |
| warmup_steps: 300 | |
| token_list: | |
| - <blank> | |
| - <unk> | |
| - ▁ | |
| - a | |
| - n | |
| - y | |
| - u | |
| - qa | |
| - s | |
| - ta | |
| - q | |
| - ri | |
| - ku | |
| - i | |
| - kuna | |
| - r | |
| - m | |
| - e | |
| - cha | |
| - pi | |
| - pa | |
| - o | |
| - lla | |
| - na | |
| - ▁kay | |
| - ▁ka | |
| - ▁chay | |
| - c | |
| - chu | |
| - ki | |
| - ▁wa | |
| - ña | |
| - w | |
| - ▁pa | |
| - ra | |
| - si | |
| - man | |
| - pas | |
| - sqa | |
| - l | |
| - tu | |
| - nku | |
| - ▁ma | |
| - yku | |
| - taq | |
| - ▁a | |
| - ▁ima | |
| - d | |
| - ti | |
| - chi | |
| - manta | |
| - ya | |
| - ka | |
| - mi | |
| - h | |
| - p | |
| - wan | |
| - nchik | |
| - ll | |
| - chkan | |
| - spa | |
| - ▁ha | |
| - ▁ni | |
| - pu | |
| - yta | |
| - chik | |
| - mun | |
| - ni | |
| - paq | |
| - sun | |
| - ▁mana | |
| - ▁wi | |
| - k | |
| - ▁allin | |
| - ▁ancha | |
| - ▁hina | |
| - rí | |
| - ▁punchaw | |
| - ▁yacha | |
| - ▁llaqta | |
| - ñ | |
| - ynin | |
| - ▁rima | |
| - b | |
| - ▁huk | |
| - skan | |
| - '''' | |
| - g | |
| - j | |
| - z | |
| - á | |
| - ó | |
| - í | |
| - ú | |
| - f | |
| - v | |
| - t | |
| - x | |
| - é | |
| - <sos/eos> | |
| init: null | |
| input_size: null | |
| ctc_conf: | |
| dropout_rate: 0.0 | |
| ctc_type: builtin | |
| reduce: true | |
| ignore_nan_grad: true | |
| joint_net_conf: null | |
| use_preprocessor: true | |
| token_type: bpe | |
| bpemodel: data/quy_token_list/bpe_unigram100/bpe.model | |
| 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' | |
| frontend: s3prl | |
| frontend_conf: | |
| frontend_conf: | |
| upstream: wav2vec2_url | |
| upstream_ckpt: https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr2_300m.pt | |
| download_dir: ./hub | |
| multilayer_feature: true | |
| fs: 16k | |
| specaug: null | |
| specaug_conf: {} | |
| normalize: utterance_mvn | |
| normalize_conf: {} | |
| model: espnet | |
| model_conf: | |
| ctc_weight: 1.0 | |
| lsm_weight: 0.0 | |
| length_normalized_loss: false | |
| extract_feats_in_collect_stats: false | |
| preencoder: linear | |
| preencoder_conf: | |
| input_size: 1024 | |
| output_size: 80 | |
| encoder: transformer | |
| encoder_conf: | |
| input_layer: conv2d2 | |
| num_blocks: 1 | |
| linear_units: 2048 | |
| dropout_rate: 0.2 | |
| output_size: 256 | |
| attention_heads: 8 | |
| attention_dropout_rate: 0.2 | |
| postencoder: null | |
| postencoder_conf: {} | |
| decoder: rnn | |
| decoder_conf: {} | |
| required: | |
| - output_dir | |
| - token_list | |
| version: '202204' | |
| distributed: false | |