2026-01-14 00:19:21 | INFO | espnet3 | === ESPnet3 run started: 2026-01-14T00:19:21.364830 === 2026-01-14 00:19:21 | INFO | espnet3 | Command: /data/user_data/msomeki/espnet3/.venv/bin/python3 run.py --stages create_dataset train_tokenizer collect_stats train infer measure --train_config conf/train.yaml --infer_config conf/infer.yaml --measure_config conf/measure.yaml 2026-01-14 00:19:21 | INFO | espnet3 | Python: 3.11.13 (main, Aug 18 2025, 19:19:13) [Clang 20.1.4 ] 2026-01-14 00:19:21 | INFO | espnet3 | Working directory: /home/msomeki/00_systems/espnet3/egs3/mini_an4/asr 2026-01-14 00:19:21 | INFO | espnet3 | train config: /home/msomeki/00_systems/espnet3/egs3/mini_an4/asr/conf/train_asr_rnn_data_aug_debug.yaml 2026-01-14 00:19:21 | INFO | espnet3 | infer config: /home/msomeki/00_systems/espnet3/egs3/mini_an4/asr/conf/infer.yaml 2026-01-14 00:19:21 | INFO | espnet3 | measure config: /home/msomeki/00_systems/espnet3/egs3/mini_an4/asr/conf/measure.yaml 2026-01-14 00:19:21 | INFO | espnet3 | Git: commit=8509faad9811b58d5024f29fb9d68ffb026b5e73, short_commit=8509faad9, branch=espnet3/recipe/asr_ls100, worktree=dirty 2026-01-14 00:19:21 | INFO | espnet3 | Cluster env: OMPI_MCA_plm_slurm_args=--external-launcher SLURM_CLUSTER_NAME=babel SLURM_CONF=/var/spool/slurmd/conf-cache/slurm.conf SLURM_CPUS_ON_NODE=1 SLURM_CPUS_PER_TASK=1 SLURM_CPU_BIND=quiet,mask_cpu:0x0000000000010000 SLURM_CPU_BIND_LIST=0x0000000000010000 SLURM_CPU_BIND_TYPE=mask_cpu: SLURM_CPU_BIND_VERBOSE=quiet SLURM_DISTRIBUTION=cyclic,pack SLURM_GTIDS=0 SLURM_JOBID=6122041 SLURM_JOB_ACCOUNT=swatanab SLURM_JOB_CPUS_PER_NODE=1 SLURM_JOB_END_TIME=1768401875 SLURM_JOB_GID=2709140 SLURM_JOB_GROUP=msomeki SLURM_JOB_ID=6122041 SLURM_JOB_NAME=bash SLURM_JOB_NODELIST=babel-o9-16 SLURM_JOB_NUM_NODES=1 SLURM_JOB_PARTITION=debug SLURM_JOB_QOS=debug_qos SLURM_JOB_START_TIME=1768358675 SLURM_JOB_UID=2709140 SLURM_JOB_USER=msomeki SLURM_LAUNCH_NODE_IPADDR=172.16.1.2 SLURM_LOCALID=0 SLURM_MEM_PER_NODE=4096 SLURM_NNODES=1 SLURM_NODEID=0 SLURM_NODELIST=babel-o9-16 SLURM_NPROCS=1 SLURM_NTASKS=1 SLURM_NTASKS_PER_NODE=1 SLURM_PRIO_PROCESS=0 SLURM_PROCID=0 SLURM_PTY_PORT=40465 SLURM_PTY_WIN_COL=112 SLURM_PTY_WIN_ROW=61 SLURM_SCRIPT_CONTEXT=prolog_task SLURM_SRUN_COMM_HOST=172.16.1.2 SLURM_SRUN_COMM_PORT=33789 SLURM_STEPID=0 SLURM_STEP_ID=0 SLURM_STEP_LAUNCHER_PORT=33789 SLURM_STEP_NODELIST=babel-o9-16 SLURM_STEP_NUM_NODES=1 SLURM_STEP_NUM_TASKS=1 SLURM_STEP_TASKS_PER_NODE=1 SLURM_SUBMIT_DIR=/home/msomeki/00_systems/espnet3 SLURM_SUBMIT_HOST=login1 SLURM_TASKS_PER_NODE=1 SLURM_TASK_PID=3334910 SLURM_TOPOLOGY_ADDR=babel-o9-16 SLURM_TOPOLOGY_ADDR_PATTERN=node SLURM_TRES_PER_TASK=cpu=1 SLURM_UMASK=0027 2026-01-14 00:19:21 | INFO | espnet3 | Runtime env: LD_LIBRARY_PATH=/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64:/home/msomeki/00_systems/espnet3/tools/espeak-ng/lib:/home/msomeki/00_systems/espnet3/tools/lib:/home/msomeki/00_systems/espnet3/tools/lib64: PATH=/home/msomeki/00_systems/espnet3/tools/ffmpeg-release:/home/msomeki/00_systems/espnet3/tools/festival/bin:/home/msomeki/00_systems/espnet3/tools/MBROLA/Bin:/home/msomeki/00_systems/espnet3/tools/espeak-ng/bin:/home/msomeki/00_systems/espnet3/tools/BeamformIt:/home/msomeki/00_systems/espnet3/tools/kenlm/build/bin:/home/msomeki/00_systems/espnet3/tools/PESQ/P862_annex_A_2005_CD/source:/home/msomeki/00_systems/espnet3/tools/nkf/nkf-2.1.4:/home/msomeki/00_systems/espnet3/tools/moses/scripts/tokenizer:/home/msomeki/00_systems/espnet3/tools/moses/scripts/generic:/home/msomeki/00_systems/espnet3/tools/tools/moses/scripts/recaser:/home/msomeki/00_systems/espnet3/tools/moses/scripts/training:/home/msomeki/00_systems/espnet3/tools/mwerSegmenter:/home/msomeki/00_systems/espnet3/tools/sctk/bin:/home/msomeki/00_systems/espnet3/tools/sph2pipe:/home/msomeki/00_systems/espnet3/tools/sentencepiece_commands:/data/user_data/msomeki/espnet3/.venv/bin:/home/msomeki/.pixi/bin:/home/msomeki/local/bin:/home/msomeki/utils:/usr/share/Modules/bin:/home/msomeki/00_systems/espnet3/tools/ffmpeg-release:/home/msomeki/00_systems/espnet3/tools/festival/bin:/home/msomeki/00_systems/espnet3/tools/MBROLA/Bin:/home/msomeki/00_systems/espnet3/tools/espeak-ng/bin:/home/msomeki/00_systems/espnet3/tools/BeamformIt:/home/msomeki/00_systems/espnet3/tools/kenlm/build/bin:/home/msomeki/00_systems/espnet3/tools/PESQ/P862_annex_A_2005_CD/source:/home/msomeki/00_systems/espnet3/tools/nkf/nkf-2.1.4:/home/msomeki/00_systems/espnet3/tools/moses/scripts/tokenizer:/home/msomeki/00_systems/espnet3/tools/moses/scripts/generic:/home/msomeki/00_systems/espnet3/tools/tools/moses/scripts/recaser:/home/msomeki/00_systems/espnet3/tools/moses/scripts/training:/home/msomeki/00_systems/espnet3/tools/mwerSegmenter:/home/msomeki/00_systems/espnet3/tools/sctk/bin:/home/msomeki/00_systems/espnet3/tools/sph2pipe:/home/msomeki/00_systems/espnet3/tools/sentencepiece_commands:/home/msomeki/00_systems/espnet3/tools/ffmpeg-release:/home/msomeki/00_systems/espnet3/tools/festival/bin:/home/msomeki/00_systems/espnet3/tools/MBROLA/Bin:/home/msomeki/00_systems/espnet3/tools/espeak-ng/bin:/home/msomeki/00_systems/espnet3/tools/BeamformIt:/home/msomeki/00_systems/espnet3/tools/kenlm/build/bin:/home/msomeki/00_systems/espnet3/tools/PESQ/P862_annex_A_2005_CD/source:/home/msomeki/00_systems/espnet3/tools/nkf/nkf-2.1.4:/home/msomeki/00_systems/espnet3/tools/moses/scripts/tokenizer:/home/msomeki/00_systems/espnet3/tools/moses/scripts/generic:/home/msomeki/00_systems/espnet3/tools/tools/moses/scripts/recaser:/home/msomeki/00_systems/espnet3/tools/moses/scripts/training:/home/msomeki/00_systems/espnet3/tools/mwerSegmenter:/home/msomeki/00_systems/espnet3/tools/sctk/bin:/home/msomeki/00_systems/espnet3/tools/sph2pipe:/home/msomeki/00_systems/espnet3/tools/sentencepiece_commands:/home/msomeki/.pixi/bin:/home/msomeki/local/bin:/home/msomeki/utils:/home/msomeki/.local/bin:/home/msomeki/bin:/usr/local/bin:/usr/bin:/usr/local/sbin:/usr/sbin PYTHONPATH=/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models:../../../:../../TEMPLATE/asr:/home/msomeki/00_systems/espnet3/egs3/mini_an4/asr:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3:/home/msomeki/00_systems/espnet3/tools/RawNet/python/RawNet3/models: 2026-01-14 00:19:21 | INFO | espnet3 | Train config content: num_device: 1 num_nodes: 1 task: espnet3.systems.asr.task.ASRTask recipe_dir: . data_dir: ./data exp_tag: train_asr_rnn_data_aug_debug exp_dir: ./exp/train_asr_rnn_data_aug_debug stats_dir: ./exp/stats decode_dir: ./exp/train_asr_rnn_data_aug_debug/decode dataset_dir: ./data/mini_an4 create_dataset: func: src.create_dataset.create_dataset dataset_dir: ./data/mini_an4 archive_path: ./../../egs2/mini_an4/asr1/downloads.tar.gz dataset: _target_: espnet3.components.data.data_organizer.DataOrganizer train: - name: train_nodev dataset: _target_: src.dataset.MiniAN4Dataset manifest_path: ./data/mini_an4/manifest/train_nodev.tsv valid: - name: train_dev dataset: _target_: src.dataset.MiniAN4Dataset manifest_path: ./data/mini_an4/manifest/train_dev.tsv preprocessor: _target_: espnet2.train.preprocessor.CommonPreprocessor _convert_: all fs: 16000 train: true data_aug_effects: - - 0.1 - contrast - enhancement_amount: 75.0 - - 0.1 - highpass - cutoff_freq: 5000 Q: 0.707 - - 0.1 - equalization - center_freq: 1000 gain: 0 Q: 0.707 - - 0.1 - - - 0.3 - speed_perturb - factor: 0.9 - - 0.3 - speed_perturb - factor: 1.1 - - 0.3 - speed_perturb - factor: 1.3 data_aug_num: - 1 - 4 data_aug_prob: 1.0 token_type: bpe token_list: ./data/bpe_30/tokens.txt bpemodel: ./data/bpe_30/bpe.model parallel: env: local n_workers: 1 options: {} dataloader: collate_fn: _target_: espnet2.train.collate_fn.CommonCollateFn int_pad_value: -1 train: multiple_iterator: false num_shards: 1 iter_factory: _target_: espnet2.iterators.sequence_iter_factory.SequenceIterFactory shuffle: true collate_fn: _target_: espnet2.train.collate_fn.CommonCollateFn int_pad_value: -1 num_workers: 0 batches: type: sorted shape_files: - ./exp/stats/train/feats_shape batch_size: 2 batch_bins: 200000 valid: multiple_iterator: false num_shards: 1 iter_factory: _target_: espnet2.iterators.sequence_iter_factory.SequenceIterFactory shuffle: false collate_fn: _target_: espnet2.train.collate_fn.CommonCollateFn int_pad_value: -1 batches: type: sorted shape_files: - ./exp/stats/valid/feats_shape batch_size: 2 batch_bins: 200000 optim: _target_: torch.optim.Adam lr: 0.001 weight_decay: 0.0 scheduler: _target_: torch.optim.lr_scheduler.ReduceLROnPlateau mode: min factor: 0.5 patience: 1 val_scheduler_criterion: valid/loss best_model_criterion: - - valid/acc - 1 - max trainer: devices: 1 num_nodes: 1 accumulate_grad_batches: 1 check_val_every_n_epoch: 1 gradient_clip_val: 1.0 log_every_n_steps: 1 max_epochs: 1 limit_train_batches: 1 limit_val_batches: 1 precision: 32 reload_dataloaders_every_n_epochs: 1 use_distributed_sampler: false tokenizer: vocab_size: 30 character_coverage: 1.0 model_type: bpe save_path: ./data/bpe_30 text_builder: func: src.tokenizer.gather_training_text manifest_path: ./data/mini_an4/manifest/train_nodev.tsv model: vocab_size: 30 token_list: ./data/bpe_30/tokens.txt encoder: vgg_rnn encoder_conf: num_layers: 1 hidden_size: 2 output_size: 2 decoder: rnn decoder_conf: hidden_size: 2 model_conf: ctc_weight: 0.3 lsm_weight: 0.1 length_normalized_loss: false frontend: default frontend_conf: n_fft: 512 win_length: 400 hop_length: 160 2026-01-14 00:19:21 | INFO | espnet3 | Infer config content: num_device: 1 num_nodes: 1 recipe_dir: . data_dir: ./data exp_tag: train_asr_rnn_data_aug_debug exp_dir: ./exp/train_asr_rnn_data_aug_debug stats_dir: ./exp/stats decode_dir: ./exp/train_asr_rnn_data_aug_debug/decode dataset_dir: ./data/mini_an4 dataset: _target_: espnet3.components.data.data_organizer.DataOrganizer test: - name: test dataset: _target_: src.dataset.MiniAN4Dataset manifest_path: ./data/mini_an4/manifest/test.tsv parallel: env: local n_workers: 1 model: _target_: espnet2.bin.asr_inference.Speech2Text asr_train_config: ./exp/train_asr_rnn_data_aug_debug/config.yaml asr_model_file: ./exp/train_asr_rnn_data_aug_debug/last.ckpt beam_size: 1 ctc_weight: 0.3 tokenizer: vocab_size: 30 character_coverage: 1.0 model_type: bpe save_path: ./data/bpe_30 2026-01-14 00:19:21 | INFO | espnet3 | Measure config content: recipe_dir: . data_dir: ./data exp_tag: train_asr_rnn_data_aug_debug exp_dir: ./exp/train_asr_rnn_data_aug_debug stats_dir: ./exp/stats decode_dir: ./exp/train_asr_rnn_data_aug_debug/decode dataset_dir: ./data/mini_an4 dataset: _target_: espnet3.components.data.data_organizer.DataOrganizer test: - name: test dataset: _target_: src.dataset.MiniAN4Dataset manifest_path: ./data/mini_an4/manifest/test.tsv metrics: - metric: _target_: espnet3.systems.asr.metrics.wer.WER clean_types: null - metric: _target_: espnet3.systems.asr.metrics.cer.CER clean_types: null 2026-01-14 00:19:21 | INFO | espnet3 | === [START] stage: train === 2026-01-14 00:19:21 | INFO | espnet3.systems.asr.system | ASRSystem.train(): starting training process 2026-01-14 00:19:21 | INFO | espnet3.systems.base.system | Training start | exp_dir=./exp/train_asr_rnn_data_aug_debug model= 2026-01-14 00:19:22 | INFO | root | Vocabulary size: 30 2026-01-14 00:19:22 | INFO | espnet3.systems.base.train | Model: ESPnetASRModel( (frontend): DefaultFrontend( (stft): Stft(n_fft=512, win_length=400, hop_length=160, center=True, normalized=False, onesided=True) (frontend): Frontend() (logmel): LogMel(sr=16000, n_fft=512, n_mels=80, fmin=0, fmax=8000.0, htk=False) ) (normalize): UtteranceMVN(norm_means=True, norm_vars=False) (encoder): VGGRNNEncoder( (enc): ModuleList( (0): VGG2L( (conv1_1): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv1_2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2_1): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (conv2_2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): RNNP( (birnn0): LSTM(2560, 2, batch_first=True, bidirectional=True) (bt0): Linear(in_features=4, out_features=2, bias=True) ) ) ) (decoder): RNNDecoder( (embed): Embedding(30, 2) (dropout_emb): Dropout(p=0.0, inplace=False) (decoder): ModuleList( (0): LSTMCell(4, 2) ) (dropout_dec): ModuleList( (0): Dropout(p=0.0, inplace=False) ) (output): Linear(in_features=2, out_features=30, bias=True) (att_list): ModuleList( (0): AttLoc( (mlp_enc): Linear(in_features=2, out_features=320, bias=True) (mlp_dec): Linear(in_features=2, out_features=320, bias=False) (mlp_att): Linear(in_features=10, out_features=320, bias=False) (loc_conv): Conv2d(1, 10, kernel_size=(1, 201), stride=(1, 1), padding=(0, 100), bias=False) (gvec): Linear(in_features=320, out_features=1, bias=True) ) ) ) (criterion_att): LabelSmoothingLoss( (criterion): KLDivLoss() ) (ctc): CTC( (ctc_lo): Linear(in_features=2, out_features=30, bias=True) (ctc_loss): CTCLoss() ) ) 2026-01-14 00:19:22 | WARNING | py.warnings | /data/user_data/msomeki/espnet3/.venv/lib/python3.11/site-packages/lightning/fabric/plugins/environments/slurm.py:204: The `srun` command is available on your system but is not used. HINT: If your intention is to run Lightning on SLURM, prepend your python command with `srun` like so: srun python3 run.py --stages create_dataset train_tokenizer coll ... 2026-01-14 00:19:22 | INFO | lightning.pytorch.utilities.rank_zero | GPU available: False, used: False 2026-01-14 00:19:22 | INFO | lightning.pytorch.utilities.rank_zero | TPU available: False, using: 0 TPU cores 2026-01-14 00:19:22 | INFO | lightning.pytorch.utilities.rank_zero | `Trainer(limit_train_batches=1)` was configured so 1 batch per epoch will be used. 2026-01-14 00:19:22 | INFO | lightning.pytorch.utilities.rank_zero | `Trainer(limit_val_batches=1)` was configured so 1 batch will be used. 2026-01-14 00:19:22 | WARNING | py.warnings | /data/user_data/msomeki/espnet3/.venv/lib/python3.11/site-packages/lightning/pytorch/callbacks/model_checkpoint.py:881: Checkpoint directory /home/msomeki/00_systems/espnet3/egs3/mini_an4/asr/exp/train_asr_rnn_data_aug_debug exists and is not empty. 2026-01-14 00:19:22 | INFO | lightning.pytorch.callbacks.model_summary | | Name | Type | Params | Mode | FLOPs --------------------------------------------------------- 0 | model | ESPnetASRModel | 307 K | train | 0 --------------------------------------------------------- 307 K Trainable params 0 Non-trainable params 307 K Total params 1.230 Total estimated model params size (MB) 35 Modules in train mode 1 Modules in eval mode 0 Total Flops 2026-01-14 00:19:22 | WARNING | py.warnings | /home/msomeki/00_systems/espnet3/espnet2/asr/espnet_model.py:402: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(self.autocast_frontend, dtype=autocast_type): 2026-01-14 00:19:22 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:22 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:22 | WARNING | py.warnings | /data/user_data/msomeki/espnet3/.venv/lib/python3.11/site-packages/lightning/pytorch/loops/fit_loop.py:534: Found 1 module(s) in eval mode at the start of training. This may lead to unexpected behavior during training. If this is intentional, you can ignore this warning. 2026-01-14 00:19:22 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:23 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:23 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:23 | WARNING | root | Using make_pad_mask with a list of lengths is not tracable. If you try to trace this function with type(lengths) == list, please change the type of lengths to torch.LongTensor. 2026-01-14 00:19:23 | INFO | lightning.pytorch.utilities.rank_zero | `Trainer.fit` stopped: `max_epochs=1` reached. 2026-01-14 00:19:23 | INFO | espnet3.systems.base.train | Training finished in 1.46s | exp_dir=./exp/train_asr_rnn_data_aug_debug model=None 2026-01-14 00:19:23 | INFO | espnet3 | === [DONE] stage: train (1.47s) ===