| 05/22/2023 13:20:20 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 2distributed training: True, 16-bits training: True | |
| 05/22/2023 13:20:20 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( | |
| _n_gpu=2, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_pin_memory=True, | |
| ddp_backend=None, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=1000, | |
| evaluation_strategy=steps, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_config={'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| generation_config=None, | |
| generation_max_length=225, | |
| generation_num_beams=None, | |
| gradient_accumulation_steps=8, | |
| gradient_checkpointing=True, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=every_save, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=1.75e-05, | |
| length_column_name=input_length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=./runs/May22_13-20-19_crimv3mgpu016, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=25, | |
| logging_strategy=steps, | |
| lr_scheduler_type=linear, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=wer, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=30.0, | |
| optim=adamw_hf, | |
| optim_args=None, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=32, | |
| per_device_train_batch_size=32, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['wandb'], | |
| resume_from_checkpoint=None, | |
| run_name=./, | |
| save_on_each_node=False, | |
| save_safetensors=False, | |
| save_steps=1000, | |
| save_strategy=steps, | |
| save_total_limit=None, | |
| seed=42, | |
| sharded_ddp=[], | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=4000, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| 05/22/2023 13:20:20 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( | |
| _n_gpu=2, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_pin_memory=True, | |
| ddp_backend=None, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=1000, | |
| evaluation_strategy=steps, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_config={'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| generation_config=None, | |
| generation_max_length=225, | |
| generation_num_beams=None, | |
| gradient_accumulation_steps=8, | |
| gradient_checkpointing=True, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=every_save, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=1.75e-05, | |
| length_column_name=input_length, | |
| load_best_model_at_end=True, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=./runs/May22_13-20-19_crimv3mgpu016, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=25, | |
| logging_strategy=steps, | |
| lr_scheduler_type=linear, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=wer, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=30.0, | |
| optim=adamw_hf, | |
| optim_args=None, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=32, | |
| per_device_train_batch_size=32, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['wandb'], | |
| resume_from_checkpoint=None, | |
| run_name=./, | |
| save_on_each_node=False, | |
| save_safetensors=False, | |
| save_steps=1000, | |
| save_strategy=steps, | |
| save_total_limit=None, | |
| seed=42, | |
| sharded_ddp=[], | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=4000, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| [INFO|configuration_utils.py:669] 2023-05-22 13:20:37,583 >> loading configuration file config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/config.json | |
| [INFO|configuration_utils.py:725] 2023-05-22 13:20:37,651 >> Model config WhisperConfig { | |
| "_name_or_path": "openai/whisper-small", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "apply_spec_augment": false, | |
| "architectures": [ | |
| "WhisperForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.0, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "classifier_proj_size": 256, | |
| "d_model": 768, | |
| "decoder_attention_heads": 12, | |
| "decoder_ffn_dim": 3072, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 50258, | |
| "dropout": 0.0, | |
| "encoder_attention_heads": 12, | |
| "encoder_ffn_dim": 3072, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 50257, | |
| "forced_decoder_ids": [ | |
| [ | |
| 1, | |
| 50259 | |
| ], | |
| [ | |
| 2, | |
| 50359 | |
| ], | |
| [ | |
| 3, | |
| 50363 | |
| ] | |
| ], | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "mask_feature_length": 10, | |
| "mask_feature_min_masks": 0, | |
| "mask_feature_prob": 0.0, | |
| "mask_time_length": 10, | |
| "mask_time_min_masks": 2, | |
| "mask_time_prob": 0.05, | |
| "max_length": 448, | |
| "max_source_positions": 1500, | |
| "max_target_positions": 448, | |
| "model_type": "whisper", | |
| "num_hidden_layers": 12, | |
| "num_mel_bins": 80, | |
| "pad_token_id": 50257, | |
| "scale_embedding": false, | |
| "suppress_tokens": [ | |
| 1, | |
| 2, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 14, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31, | |
| 58, | |
| 59, | |
| 60, | |
| 61, | |
| 62, | |
| 63, | |
| 90, | |
| 91, | |
| 92, | |
| 93, | |
| 359, | |
| 503, | |
| 522, | |
| 542, | |
| 873, | |
| 893, | |
| 902, | |
| 918, | |
| 922, | |
| 931, | |
| 1350, | |
| 1853, | |
| 1982, | |
| 2460, | |
| 2627, | |
| 3246, | |
| 3253, | |
| 3268, | |
| 3536, | |
| 3846, | |
| 3961, | |
| 4183, | |
| 4667, | |
| 6585, | |
| 6647, | |
| 7273, | |
| 9061, | |
| 9383, | |
| 10428, | |
| 10929, | |
| 11938, | |
| 12033, | |
| 12331, | |
| 12562, | |
| 13793, | |
| 14157, | |
| 14635, | |
| 15265, | |
| 15618, | |
| 16553, | |
| 16604, | |
| 18362, | |
| 18956, | |
| 20075, | |
| 21675, | |
| 22520, | |
| 26130, | |
| 26161, | |
| 26435, | |
| 28279, | |
| 29464, | |
| 31650, | |
| 32302, | |
| 32470, | |
| 36865, | |
| 42863, | |
| 47425, | |
| 49870, | |
| 50254, | |
| 50258, | |
| 50360, | |
| 50361, | |
| 50362 | |
| ], | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.29.0.dev0", | |
| "use_cache": true, | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 51865 | |
| } | |
| [INFO|feature_extraction_utils.py:469] 2023-05-22 13:20:37,926 >> loading configuration file preprocessor_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/preprocessor_config.json | |
| [INFO|feature_extraction_utils.py:511] 2023-05-22 13:20:37,955 >> Feature extractor WhisperFeatureExtractor { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file vocab.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/vocab.json | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file tokenizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer.json | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file merges.txt from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/merges.txt | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file normalizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/normalizer.json | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file added_tokens.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/added_tokens.json | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file special_tokens_map.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file tokenizer_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer_config.json | |
| [INFO|modeling_utils.py:2542] 2023-05-22 13:20:38,651 >> loading weights file pytorch_model.bin from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/pytorch_model.bin | |
| [INFO|configuration_utils.py:577] 2023-05-22 13:20:47,050 >> Generate config GenerationConfig { | |
| "_from_model_config": true, | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "decoder_start_token_id": 50258, | |
| "eos_token_id": 50257, | |
| "max_length": 448, | |
| "pad_token_id": 50257, | |
| "transformers_version": "4.29.0.dev0", | |
| "use_cache": false | |
| } | |
| [INFO|modeling_utils.py:3211] 2023-05-22 13:20:49,666 >> All model checkpoint weights were used when initializing WhisperForConditionalGeneration. | |
| [INFO|modeling_utils.py:3219] 2023-05-22 13:20:49,666 >> All the weights of WhisperForConditionalGeneration were initialized from the model checkpoint at openai/whisper-small. | |
| If your task is similar to the task the model of the checkpoint was trained on, you can already use WhisperForConditionalGeneration for predictions without further training. | |
| [INFO|configuration_utils.py:539] 2023-05-22 13:20:50,330 >> loading configuration file generation_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/generation_config.json | |
| [INFO|configuration_utils.py:577] 2023-05-22 13:20:50,331 >> Generate config GenerationConfig { | |
| "begin_suppress_tokens": [ | |
| 220, | |
| 50257 | |
| ], | |
| "bos_token_id": 50257, | |
| "decoder_start_token_id": 50258, | |
| "eos_token_id": 50257, | |
| "forced_decoder_ids": [ | |
| [ | |
| 1, | |
| null | |
| ], | |
| [ | |
| 2, | |
| 50359 | |
| ] | |
| ], | |
| "is_multilingual": true, | |
| "lang_to_id": { | |
| "<|af|>": 50327, | |
| "<|am|>": 50334, | |
| "<|ar|>": 50272, | |
| "<|as|>": 50350, | |
| "<|az|>": 50304, | |
| "<|ba|>": 50355, | |
| "<|be|>": 50330, | |
| "<|bg|>": 50292, | |
| "<|bn|>": 50302, | |
| "<|bo|>": 50347, | |
| "<|br|>": 50309, | |
| "<|bs|>": 50315, | |
| "<|ca|>": 50270, | |
| "<|cs|>": 50283, | |
| "<|cy|>": 50297, | |
| "<|da|>": 50285, | |
| "<|de|>": 50261, | |
| "<|el|>": 50281, | |
| "<|en|>": 50259, | |
| "<|es|>": 50262, | |
| "<|et|>": 50307, | |
| "<|eu|>": 50310, | |
| "<|fa|>": 50300, | |
| "<|fi|>": 50277, | |
| "<|fo|>": 50338, | |
| "<|fr|>": 50265, | |
| "<|gl|>": 50319, | |
| "<|gu|>": 50333, | |
| "<|haw|>": 50352, | |
| "<|ha|>": 50354, | |
| "<|he|>": 50279, | |
| "<|hi|>": 50276, | |
| "<|hr|>": 50291, | |
| "<|ht|>": 50339, | |
| "<|hu|>": 50286, | |
| "<|hy|>": 50312, | |
| "<|id|>": 50275, | |
| "<|is|>": 50311, | |
| "<|it|>": 50274, | |
| "<|ja|>": 50266, | |
| "<|jw|>": 50356, | |
| "<|ka|>": 50329, | |
| "<|kk|>": 50316, | |
| "<|km|>": 50323, | |
| "<|kn|>": 50306, | |
| "<|ko|>": 50264, | |
| "<|la|>": 50294, | |
| "<|lb|>": 50345, | |
| "<|ln|>": 50353, | |
| "<|lo|>": 50336, | |
| "<|lt|>": 50293, | |
| "<|lv|>": 50301, | |
| "<|mg|>": 50349, | |
| "<|mi|>": 50295, | |
| "<|mk|>": 50308, | |
| "<|ml|>": 50296, | |
| "<|mn|>": 50314, | |
| "<|mr|>": 50320, | |
| "<|ms|>": 50282, | |
| "<|mt|>": 50343, | |
| "<|my|>": 50346, | |
| "<|ne|>": 50313, | |
| "<|nl|>": 50271, | |
| "<|nn|>": 50342, | |
| "<|no|>": 50288, | |
| "<|oc|>": 50328, | |
| "<|pa|>": 50321, | |
| "<|pl|>": 50269, | |
| "<|ps|>": 50340, | |
| "<|pt|>": 50267, | |
| "<|ro|>": 50284, | |
| "<|ru|>": 50263, | |
| "<|sa|>": 50344, | |
| "<|sd|>": 50332, | |
| "<|si|>": 50322, | |
| "<|sk|>": 50298, | |
| "<|sl|>": 50305, | |
| "<|sn|>": 50324, | |
| "<|so|>": 50326, | |
| "<|sq|>": 50317, | |
| "<|sr|>": 50303, | |
| "<|su|>": 50357, | |
| "<|sv|>": 50273, | |
| "<|sw|>": 50318, | |
| "<|ta|>": 50287, | |
| "<|te|>": 50299, | |
| "<|tg|>": 50331, | |
| "<|th|>": 50289, | |
| "<|tk|>": 50341, | |
| "<|tl|>": 50348, | |
| "<|tr|>": 50268, | |
| "<|tt|>": 50351, | |
| "<|uk|>": 50280, | |
| "<|ur|>": 50290, | |
| "<|uz|>": 50337, | |
| "<|vi|>": 50278, | |
| "<|yi|>": 50335, | |
| "<|yo|>": 50325, | |
| "<|zh|>": 50260 | |
| }, | |
| "max_initial_timestamp_index": 1, | |
| "max_length": 448, | |
| "no_timestamps_token_id": 50363, | |
| "pad_token_id": 50257, | |
| "return_timestamps": false, | |
| "suppress_tokens": [ | |
| 1, | |
| 2, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 14, | |
| 25, | |
| 26, | |
| 27, | |
| 28, | |
| 29, | |
| 31, | |
| 58, | |
| 59, | |
| 60, | |
| 61, | |
| 62, | |
| 63, | |
| 90, | |
| 91, | |
| 92, | |
| 93, | |
| 359, | |
| 503, | |
| 522, | |
| 542, | |
| 873, | |
| 893, | |
| 902, | |
| 918, | |
| 922, | |
| 931, | |
| 1350, | |
| 1853, | |
| 1982, | |
| 2460, | |
| 2627, | |
| 3246, | |
| 3253, | |
| 3268, | |
| 3536, | |
| 3846, | |
| 3961, | |
| 4183, | |
| 4667, | |
| 6585, | |
| 6647, | |
| 7273, | |
| 9061, | |
| 9383, | |
| 10428, | |
| 10929, | |
| 11938, | |
| 12033, | |
| 12331, | |
| 12562, | |
| 13793, | |
| 14157, | |
| 14635, | |
| 15265, | |
| 15618, | |
| 16553, | |
| 16604, | |
| 18362, | |
| 18956, | |
| 20075, | |
| 21675, | |
| 22520, | |
| 26130, | |
| 26161, | |
| 26435, | |
| 28279, | |
| 29464, | |
| 31650, | |
| 32302, | |
| 32470, | |
| 36865, | |
| 42863, | |
| 47425, | |
| 49870, | |
| 50254, | |
| 50258, | |
| 50358, | |
| 50359, | |
| 50360, | |
| 50361, | |
| 50362 | |
| ], | |
| "task_to_id": { | |
| "transcribe": 50359, | |
| "translate": 50358 | |
| }, | |
| "transformers_version": "4.29.0.dev0" | |
| } | |
| [INFO|feature_extraction_utils.py:369] 2023-05-22 13:20:52,959 >> Feature extractor saved in ./preprocessor_config.json | |
| [INFO|tokenization_utils_base.py:2181] 2023-05-22 13:20:52,962 >> tokenizer config file saved in ./tokenizer_config.json | |
| [INFO|tokenization_utils_base.py:2188] 2023-05-22 13:20:52,965 >> Special tokens file saved in ./special_tokens_map.json | |
| [INFO|configuration_utils.py:458] 2023-05-22 13:20:53,103 >> Configuration saved in ./config.json | |
| [INFO|image_processing_utils.py:307] 2023-05-22 13:20:53,104 >> loading configuration file ./preprocessor_config.json | |
| [INFO|feature_extraction_utils.py:467] 2023-05-22 13:20:53,134 >> loading configuration file ./preprocessor_config.json | |
| [INFO|feature_extraction_utils.py:511] 2023-05-22 13:20:53,135 >> Feature extractor WhisperFeatureExtractor { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file vocab.json | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file tokenizer.json | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file merges.txt | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file normalizer.json | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file added_tokens.json | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file special_tokens_map.json | |
| [INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file tokenizer_config.json | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,201 >> Adding <|startoftranscript|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,201 >> Adding <|en|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|zh|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|de|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|es|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ru|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ko|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|fr|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ja|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|pt|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|tr|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|pl|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ca|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|nl|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ar|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|sv|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|it|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|id|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hi|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|fi|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|vi|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|he|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|uk|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|el|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ms|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|cs|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ro|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|da|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hu|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ta|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|no|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|th|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ur|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hr|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|bg|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|lt|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|la|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|mi|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ml|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|cy|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|sk|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|te|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|fa|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|lv|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|bn|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sr|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|az|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sl|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|kn|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|et|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mk|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|br|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|eu|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|is|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|hy|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ne|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mn|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|bs|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|kk|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sq|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sw|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|gl|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mr|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|pa|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|si|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|km|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sn|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|yo|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|so|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|af|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|oc|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ka|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|be|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|tg|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sd|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|gu|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|am|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|yi|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|lo|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|uz|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|fo|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ht|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ps|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tk|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|nn|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|mt|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|sa|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|lb|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|my|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|bo|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tl|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|mg|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|as|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tt|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|haw|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ln|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ha|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ba|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|jw|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|su|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|translate|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|transcribe|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|startoflm|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|startofprev|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|nocaptions|> to the vocabulary | |
| [INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|notimestamps|> to the vocabulary | |
| /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./ is already a clone of https://huggingface.co/danielizham/whisper-small-ar. Make sure you pull the latest changes with `repo.git_pull()`. | |
| 05/22/2023 13:21:02 - WARNING - huggingface_hub.repository - /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./ is already a clone of https://huggingface.co/danielizham/whisper-small-ar. Make sure you pull the latest changes with `repo.git_pull()`. | |
| Traceback (most recent call last): | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 987, in git_pull | |
| result = run_subprocess(command, self.local_dir) | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/utils/_subprocess.py", line 83, in run_subprocess | |
| return subprocess.run( | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/subprocess.py", line 528, in run | |
| raise CalledProcessError(retcode, process.args, | |
| subprocess.CalledProcessError: Command '['git', 'pull']' returned non-zero exit status 128. | |
| During handling of the above exception, another exception occurred: | |
| Traceback (most recent call last): | |
| File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 629, in <module> | |
| main() | |
| File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 560, in main | |
| trainer = Seq2SeqTrainer( | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer_seq2seq.py", line 56, in __init__ | |
| super().__init__( | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 551, in __init__ | |
| self.init_git_repo(at_init=True) | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 3516, in init_git_repo | |
| self.repo.git_pull() | |
| File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 990, in git_pull | |
| raise EnvironmentError(exc.stderr) | |
| OSError: error: cannot pull with rebase: You have unstaged changes. | |
| error: please commit or stash them. | |