raise FileNotFoundError("Dict not found: {}".format(args.data))

[guo-chuanchuan]

2024-02-29 19:02:44 | INFO | fairseq_cli.generate | {'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 100, 'log_format': None, 'log_file': None, 'tensorboard_logdir': None, 'wandb_project': None, 'azureml_logging': False, 'seed': 1, 'cpu': False, 'tpu': False, 'bf16': False, 'memory_efficient_bf16': False, 'fp16': False, 'memory_efficient_fp16': False, 'fp16_no_flatten_grads': False, 'fp16_init_scale': 128, 'fp16_scale_window': None, 'fp16_scale_tolerance': 0.0, 'on_cpu_convert_precision': False, 'min_loss_scale': 0.0001, 'threshold_loss_scale': None, 'amp': False, 'amp_batch_retries': 2, 'amp_init_scale': 128, 'amp_scale_window': None, 'user_dir': '/HOME/scz0a1h/run/Guocc/02_FAIRSEQ/examples/speech_text_joint_to_text', 'empty_cache_freq': 0, 'all_gather_list_size': 16384, 'model_parallel_size': 1, 'quantization_config_path': None, 'profile': False, 'reset_logging': False, 'suppress_crashes': False, 'use_plasma_view': False, 'plasma_path': '/tmp/plasma'}, 'common_eval': {'_name': None, 'path': '/HOME/scz0a1h/run/Guocc/02_ST_MODELS_PATH/joint-s2t-mustc-en-de/checkpoint_ave_10.pt', 'post_process': None, 'quiet': False, 'model_overrides': '{}', 'results_path': None}, 'distributed_training': {'_name': None, 'distributed_world_size': 1, 'distributed_num_procs': 1, 'distributed_rank': 0, 'distributed_backend': 'nccl', 'distributed_init_method': None, 'distributed_port': -1, 'device_id': 0, 'distributed_no_spawn': False, 'ddp_backend': 'pytorch_ddp', 'ddp_comm_hook': 'none', 'bucket_cap_mb': 25, 'fix_batches_to_gpus': False, 'find_unused_parameters': False, 'gradient_as_bucket_view': False, 'fast_stat_sync': False, 'heartbeat_timeout': -1, 'broadcast_buffers': False, 'slowmo_momentum': None, 'slowmo_base_algorithm': 'localsgd', 'localsgd_frequency': 3, 'nprocs_per_node': 1, 'pipeline_model_parallel': False, 'pipeline_balance': None, 'pipeline_devices': None, 'pipeline_chunks': 0, 'pipeline_encoder_balance': None, 'pipeline_encoder_devices': None, 'pipeline_decoder_balance': None, 'pipeline_decoder_devices': None, 'pipeline_checkpoint': 'never', 'zero_sharding': 'none', 'fp16': False, 'memory_efficient_fp16': False, 'tpu': False, 'no_reshard_after_forward': False, 'fp32_reduce_scatter': False, 'cpu_offload': False, 'use_sharded_state': False, 'not_fsdp_flatten_parameters': False}, 'dataset': {'_name': None, 'num_workers': 1, 'skip_invalid_size_inputs_valid_test': False, 'max_tokens': 100000, 'batch_size': 512, 'required_batch_size_multiple': 8, 'required_seq_len_multiple': 1, 'dataset_impl': None, 'data_buffer_size': 10, 'train_subset': 'train', 'valid_subset': 'valid', 'combine_valid_subsets': None, 'ignore_unused_valid_subsets': False, 'validate_interval': 1, 'validate_interval_updates': 0, 'validate_after_updates': 0, 'fixed_validation_seed': None, 'disable_validation': False, 'max_tokens_valid': 100000, 'batch_size_valid': 512, 'max_valid_steps': None, 'curriculum': 0, 'gen_subset': 'segment', 'num_shards': 1, 'shard_id': 0, 'grouped_shuffling': False, 'update_epoch_batch_itr': False, 'update_ordered_indices_seed': False}, 'optimization': {'_name': None, 'max_epoch': 0, 'max_update': 0, 'stop_time_hours': 0.0, 'clip_norm': 0.0, 'sentence_avg': False, 'update_freq': [1], 'lr': [0.25], 'stop_min_lr': -1.0, 'use_bmuf': False, 'skip_remainder_batch': False}, 'checkpoint': {'_name': None, 'save_dir': 'checkpoints', 'restore_file': 'checkpoint_last.pt', 'finetune_from_model': None, 'reset_dataloader': False, 'reset_lr_scheduler': False, 'reset_meters': False, 'reset_optimizer': False, 'optimizer_overrides': '{}', 'save_interval': 1, 'save_interval_updates': 0, 'keep_interval_updates': -1, 'keep_interval_updates_pattern': -1, 'keep_last_epochs': -1, 'keep_best_checkpoints': -1, 'no_save': False, 'no_epoch_checkpoints': False, 'no_last_checkpoints': False, 'no_save_optimizer_state': False, 'best_checkpoint_metric': 'loss', 'maximize_best_checkpoint_metric': False, 'patience': -1, 'checkpoint_suffix': '', 'checkpoint_shard_count': 1, 'load_checkpoint_on_all_dp_ranks': False, 'write_checkpoints_asynchronously': False, 'model_parallel_size': 1}, 'bmuf': {'_name': None, 'block_lr': 1.0, 'block_momentum': 0.875, 'global_sync_iter': 50, 'warmup_iterations': 500, 'use_nbm': False, 'average_sync': False, 'distributed_world_size': 1}, 'generation': {'_name': None, 'beam': 5, 'nbest': 1, 'max_len_a': 0.0, 'max_len_b': 200, 'min_len': 1, 'match_source_len': False, 'unnormalized': False, 'no_early_stop': False, 'no_beamable_mm': False, 'lenpen': 1.0, 'unkpen': 0.0, 'replace_unk': None, 'sacrebleu': False, 'score_reference': False, 'prefix_size': 0, 'no_repeat_ngram_size': 0, 'sampling': False, 'sampling_topk': -1, 'sampling_topp': -1.0, 'constraints': None, 'temperature': 1.0, 'diverse_beam_groups': -1, 'diverse_beam_strength': 0.5, 'diversity_rate': -1.0, 'print_alignment': None, 'print_step': False, 'lm_path': None, 'lm_weight': 0.0, 'iter_decode_eos_penalty': 0.0, 'iter_decode_max_iter': 10, 'iter_decode_force_max_iter': False, 'iter_decode_with_beam': 1, 'iter_decode_with_external_reranker': False, 'retain_iter_history': False, 'retain_dropout': False, 'retain_dropout_modules': None, 'decoding_format': None, 'no_seed_provided': False}, 'eval_lm': {'_name': None, 'output_word_probs': False, 'output_word_stats': False, 'context_window': 0, 'softmax_batch': 9223372036854775807}, 'interactive': {'_name': None, 'buffer_size': 0, 'input': '-'}, 'model': {'_name': 'wav2vec2', 'extractor_mode': 'default', 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': 'gelu', 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.0, 'dropout_input': 0.0, 'dropout_features': 0.0, 'final_dim': 0, 'layer_norm_first': False, 'conv_feature_layers': '[(512, 10, 5)] + [(512, 3, 2)] * 4 + [(512,2,2)] + [(512,2,2)]', 'conv_bias': False, 'logit_temp': 0.1, 'quantize_targets': False, 'quantize_input': False, 'same_quantizer': False, 'target_glu': False, 'feature_grad_mult': 1.0, 'quantizer_depth': 1, 'quantizer_factor': 3, 'latent_vars': 320, 'latent_groups': 2, 'latent_dim': 0, 'mask_length': 10, 'mask_prob': 0.65, 'mask_selection': 'static', 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_before': False, 'mask_channel_selection': 'static', 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'num_negatives': 100, 'negatives_from_everywhere': False, 'cross_sample_negatives': 0, 'codebook_negatives': 0, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'checkpoint_activations': False}, 'task': Namespace(no_progress_bar=False, log_interval=100, log_format=None, log_file=None, tensorboard_logdir=None, wandb_project=None, azureml_logging=False, seed=1, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=False, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=128, fp16_scale_window=None, fp16_scale_tolerance=0.0, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir='/HOME/scz0a1h/run/Guocc/02_FAIRSEQ/examples/speech_text_joint_to_text', empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='cross_entropy', tokenizer=None, bpe=None, optimizer=None, lr_scheduler='fixed', simul_type=None, scoring='sacrebleu', task='speech_text_joint_to_text', num_workers=1, skip_invalid_size_inputs_valid_test=False, max_tokens=100000, batch_size=512, required_batch_size_multiple=8, required_seq_len_multiple=1, dataset_impl=None, data_buffer_size=10, train_subset='train', valid_subset='valid', combine_valid_subsets=None, ignore_unused_valid_subsets=False, validate_interval=1, validate_interval_updates=0, validate_after_updates=0, fixed_validation_seed=None, disable_validation=False, max_tokens_valid=100000, batch_size_valid=512, max_valid_steps=None, curriculum=0, gen_subset='segment', num_shards=1, shard_id=0, grouped_shuffling=False, update_epoch_batch_itr=False, update_ordered_indices_seed=False, distributed_world_size=1, distributed_num_procs=1, distributed_rank=0, distributed_backend='nccl', distributed_init_method=None, distributed_port=-1, device_id=0, distributed_no_spawn=False, ddp_backend='pytorch_ddp', ddp_comm_hook='none', bucket_cap_mb=25, fix_batches_to_gpus=False, find_unused_parameters=False, gradient_as_bucket_view=False, fast_stat_sync=False, heartbeat_timeout=-1, broadcast_buffers=False, slowmo_momentum=None, slowmo_base_algorithm='localsgd', localsgd_frequency=3, nprocs_per_node=1, pipeline_model_parallel=False, pipeline_balance=None, pipeline_devices=None, pipeline_chunks=0, pipeline_encoder_balance=None, pipeline_encoder_devices=None, pipeline_decoder_balance=None, pipeline_decoder_devices=None, pipeline_checkpoint='never', zero_sharding='none', no_reshard_after_forward=False, fp32_reduce_scatter=False, cpu_offload=False, use_sharded_state=False, not_fsdp_flatten_parameters=False, path='/HOME/scz0a1h/run/Guocc/02_ST_MODELS_PATH/joint-s2t-mustc-en-de/checkpoint_ave_10.pt', post_process=None, quiet=False, model_overrides='{}', results_path=None, beam=5, nbest=1, max_len_a=0, max_len_b=200, min_len=1, match_source_len=False, unnormalized=False, no_early_stop=False, no_beamable_mm=False, lenpen=1.0, unkpen=0, replace_unk=None, sacrebleu=False, score_reference=False, prefix_size=0, no_repeat_ngram_size=0, sampling=False, sampling_topk=-1, sampling_topp=-1.0, constraints=None, temperature=1.0, diverse_beam_groups=-1, diverse_beam_strength=0.5, diversity_rate=-1.0, print_alignment=None, print_step=False, lm_path=None, lm_weight=0.0, iter_decode_eos_penalty=0.0, iter_decode_max_iter=10, iter_decode_force_max_iter=False, iter_decode_with_beam=1, iter_decode_with_external_reranker=False, retain_iter_history=False, retain_dropout=False, retain_dropout_modules=None, decoding_format=None, no_seed_provided=False, save_dir='checkpoints', restore_file='checkpoint_last.pt', finetune_from_model=None, reset_dataloader=False, reset_lr_scheduler=False, reset_meters=False, reset_optimizer=False, optimizer_overrides='{}', save_interval=1, save_interval_updates=0, keep_interval_updates=-1, keep_interval_updates_pattern=-1, keep_last_epochs=-1, keep_best_checkpoints=-1, no_save=False, no_epoch_checkpoints=False, no_last_checkpoints=False, no_save_optimizer_state=False, best_checkpoint_metric='loss', maximize_best_checkpoint_metric=False, patience=-1, checkpoint_suffix='', checkpoint_shard_count=1, load_checkpoint_on_all_dp_ranks=False, write_checkpoints_asynchronously=False, arch='wav2vec2', data='/HOME/scz0a1h/run/Guocc/2024_2_29_2_run', config_yaml='/HOME/scz0a1h/run/Guocc/02_ST_MODELS_PATH/joint-s2t-mustc-en-de/config.yaml', max_source_positions=12000, max_target_positions=1024, parallel_text_data='', max_tokens_text=None, max_positions_text=400, langpairs=None, speech_sample_ratio=1, text_sample_ratio=1, update_mix_data=False, load_speech_only=True, mask_text_ratio=0.0, mask_text_type='random', noise_token='', infer_target_lang='', force_anneal=None, lr_shrink=0.1, warmup_updates=0, sacrebleu_tokenizer='13a', sacrebleu_lowercase=False, sacrebleu_char_level=False, _name='speech_text_joint_to_text'), 'criterion': {'_name': 'cross_entropy', 'sentence_avg': True}, 'optimizer': None, 'lr_scheduler': {'_name': 'fixed', 'force_anneal': None, 'lr_shrink': 0.1, 'warmup_updates': 0, 'lr': [0.25]}, 'scoring': {'_name': 'sacrebleu', 'sacrebleu_tokenizer': '13a', 'sacrebleu_lowercase': False, 'sacrebleu_char_level': False}, 'bpe': None, 'tokenizer': None, 'ema': {'_name': None, 'store_ema': False, 'ema_decay': 0.9999, 'ema_start_update': 0, 'ema_seed_model': None, 'ema_update_freq': 1, 'ema_fp32': False}, 'simul_type': None}
Traceback (most recent call last):
File "/HOME/scz0a1h/.conda/envs/shas/bin/fairseq-generate", line 33, in
sys.exit(load_entry_point('fairseq', 'console_scripts', 'fairseq-generate')())
File "/data/run01/scz0a1h/Guocc/02_FAIRSEQ/fairseq_cli/generate.py", line 410, in cli_main
main(args)
File "/data/run01/scz0a1h/Guocc/02_FAIRSEQ/fairseq_cli/generate.py", line 49, in main
return _main(cfg, sys.stdout)
File "/data/run01/scz0a1h/Guocc/02_FAIRSEQ/fairseq_cli/generate.py", line 82, in _main
task = tasks.setup_task(cfg.task)
File "/data/run01/scz0a1h/Guocc/02_FAIRSEQ/fairseq/tasks/init.py", line 46, in setup_task
return task.setup_task(cfg, **kwargs)
File "/HOME/scz0a1h/run/Guocc/02_FAIRSEQ/examples/speech_text_joint_to_text/tasks/speech_text_joint.py", line 138, in setup_task
raise FileNotFoundError("Dict not found: {}".format(args.data))
FileNotFoundError: Dict not found: /HOME/scz0a1h/run/Guocc/2024_2_29_2_run