config: conf/tuning/train_asr_hubert_transformer_adam_specaug.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word 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: 200 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - train - loss - min - - valid - loss - min - - train - acc - max - - valid - acc - max keep_nbest_models: 5 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_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 num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null 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: folded 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/wav.scp - speech - sound - - dump/raw/train/text - text - text valid_data_path_and_name_and_type: - - dump/raw/valid/wav.scp - speech - sound - - dump/raw/valid/text - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.0002 scheduler: warmuplr scheduler_conf: warmup_steps: 25000 token_list: - - - the - Turn - in - lights - 'on' - up - down - temperature - heat - 'off' - Switch - increase_volume_none - kitchen - language - decrease_volume_none - bedroom - washroom - volume - my - to - bathroom - Decrease - increase_heat_washroom - decrease_heat_washroom - Increase - music - heating - Bring - increase_heat_none - decrease_heat_none - me - change_language_none_none - activate_lights_washroom - Set - Lights - activate_lights_kitchen - I - activate_music_none - too - it - increase_heat_bedroom - decrease_heat_bedroom - sound - increase_heat_kitchen - decrease_heat_kitchen - deactivate_music_none - lamp - Make - deactivate_lights_bedroom - deactivate_lights_kitchen - bring_newspaper_none - newspaper - activate_lights_bedroom - bring_socks_none - socks - bring_shoes_none - shoes - need - Volume - activate_lights_none - deactivate_lights_none - bring_juice_none - juice - deactivate_lights_washroom - change_language_Chinese_none - deactivate_lamp_none - activate_lamp_none - Kitchen - turn - some - Could - you - Bedroom - Go - get - Washroom - Chinese - phone's - change_language_English_none - Get - change_language_Korean_none - OK - now - switch - main - change_language_German_none - practice - Louder - Stop - loud - increase - Play - hear - Change - quiet - Bathroom - Fetch - Korean - English - German - Pause - Lamp - Resume - louder - Heat - audio - Its - loud, - heating? - Far - a - different - please? - decrease - Too - settings - Put - Start - Quieter - please - Thats - softer - max - mute - lower - phone - couldn't - anything, - Reduce - this, - More - That's - Lower - levels - Use - hotter - languages - Allow - can't - that - Less - system - cooler - This - video - is - low, - device - Chinese. - quieter - English. - Language - Open - German. - Korean. - init: null input_size: null ctc_conf: dropout_rate: 0.0 ctc_type: builtin reduce: true ignore_nan_grad: true model_conf: ctc_weight: 0.3 lsm_weight: 0.1 length_normalized_loss: false extract_feats_in_collect_stats: false use_preprocessor: true token_type: word 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' frontend: s3prl frontend_conf: frontend_conf: upstream: hubert_large_ll60k download_dir: ./hub multilayer_feature: true 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: utterance_mvn normalize_conf: {} preencoder: linear preencoder_conf: input_size: 1024 output_size: 80 encoder: transformer encoder_conf: output_size: 256 attention_heads: 4 linear_units: 2048 num_blocks: 12 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.0 input_layer: conv2d normalize_before: true 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: 0.0 src_attention_dropout_rate: 0.0 required: - output_dir - token_list version: 0.10.3a2 distributed: false