| loading configuration file https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv/resolve/main/config.json from cache at /home/cahya/.cache/huggingface/transformers/47f005d7b541562c0734cfe1b8aaf7f644846084b33a9247f5810d5a16d001a7.1c2175954f7220a41c71683d239699eb295d40ec92ac51faac3b85ad4bef2ad8 | |
| /home/cahya/Work/MachineLearning/transformers/src/transformers/configuration_utils.py:353: UserWarning: Passing `gradient_checkpointing` to a config initialization is deprecated and will be removed in v5 Transformers. Using `model.gradient_checkpointing_enable()` instead, or if you are using the `Trainer` API, pass `gradient_checkpointing=True` in your `TrainingArguments`. | |
| warnings.warn( | |
| Model config Wav2Vec2Config { | |
| "_name_or_path": "cahya/wav2vec2-base-turkish-artificial-cv", | |
| "activation_dropout": 0.055, | |
| "adapter_kernel_size": 3, | |
| "adapter_stride": 2, | |
| "add_adapter": false, | |
| "apply_spec_augment": true, | |
| "architectures": [ | |
| "Wav2Vec2ForCTC" | |
| ], | |
| "attention_dropout": 0.094, | |
| "bos_token_id": 1, | |
| "classifier_proj_size": 256, | |
| "codevector_dim": 256, | |
| "contrastive_logits_temperature": 0.1, | |
| "conv_bias": false, | |
| "conv_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512 | |
| ], | |
| "conv_kernel": [ | |
| 10, | |
| 3, | |
| 3, | |
| 3, | |
| 3, | |
| 2, | |
| 2 | |
| ], | |
| "conv_stride": [ | |
| 5, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "ctc_loss_reduction": "mean", | |
| "ctc_zero_infinity": true, | |
| "diversity_loss_weight": 0.1, | |
| "do_stable_layer_norm": false, | |
| "eos_token_id": 2, | |
| "feat_extract_activation": "gelu", | |
| "feat_extract_norm": "group", | |
| "feat_proj_dropout": 0.04, | |
| "feat_quantizer_dropout": 0.0, | |
| "final_dropout": 0.1, | |
| "gradient_checkpointing": true, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.047, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "layerdrop": 0.041, | |
| "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": 0.4, | |
| "model_type": "wav2vec2", | |
| "num_adapter_layers": 3, | |
| "num_attention_heads": 12, | |
| "num_codevector_groups": 2, | |
| "num_codevectors_per_group": 320, | |
| "num_conv_pos_embedding_groups": 16, | |
| "num_conv_pos_embeddings": 128, | |
| "num_feat_extract_layers": 7, | |
| "num_hidden_layers": 12, | |
| "num_negatives": 100, | |
| "output_hidden_size": 768, | |
| "pad_token_id": 39, | |
| "proj_codevector_dim": 256, | |
| "tdnn_dilation": [ | |
| 1, | |
| 2, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "tdnn_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 1500 | |
| ], | |
| "tdnn_kernel": [ | |
| 5, | |
| 3, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "transformers_version": "4.17.0.dev0", | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 40, | |
| "xvector_output_dim": 512 | |
| } | |
| 0%| | 0/1 [00:00<?, ?ba/s] 100%|██████████| 1/1 [00:00<00:00, 9.35ba/s] 100%|██████████| 1/1 [00:00<00:00, 9.34ba/s] | |
| 0%| | 0/1 [00:00<?, ?ba/s] 100%|██████████| 1/1 [00:00<00:00, 25.43ba/s] | |
| Didn't find file ./output/tokenizer_config.json. We won't load it. | |
| Didn't find file ./output/added_tokens.json. We won't load it. | |
| Didn't find file ./output/special_tokens_map.json. We won't load it. | |
| Didn't find file ./output/tokenizer.json. We won't load it. | |
| loading file ./output/vocab.json | |
| loading file None | |
| loading file None | |
| loading file None | |
| loading file None | |
| file ./output/config.json not found | |
| Adding <s> to the vocabulary | |
| Adding </s> to the vocabulary | |
| Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. | |
| loading configuration file https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv/resolve/main/config.json from cache at /home/cahya/.cache/huggingface/transformers/47f005d7b541562c0734cfe1b8aaf7f644846084b33a9247f5810d5a16d001a7.1c2175954f7220a41c71683d239699eb295d40ec92ac51faac3b85ad4bef2ad8 | |
| Model config Wav2Vec2Config { | |
| "_name_or_path": "cahya/wav2vec2-base-turkish-artificial-cv", | |
| "activation_dropout": 0.055, | |
| "adapter_kernel_size": 3, | |
| "adapter_stride": 2, | |
| "add_adapter": false, | |
| "apply_spec_augment": true, | |
| "architectures": [ | |
| "Wav2Vec2ForCTC" | |
| ], | |
| "attention_dropout": 0.094, | |
| "bos_token_id": 1, | |
| "classifier_proj_size": 256, | |
| "codevector_dim": 256, | |
| "contrastive_logits_temperature": 0.1, | |
| "conv_bias": false, | |
| "conv_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 512 | |
| ], | |
| "conv_kernel": [ | |
| 10, | |
| 3, | |
| 3, | |
| 3, | |
| 3, | |
| 2, | |
| 2 | |
| ], | |
| "conv_stride": [ | |
| 5, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "ctc_loss_reduction": "mean", | |
| "ctc_zero_infinity": true, | |
| "diversity_loss_weight": 0.1, | |
| "do_stable_layer_norm": false, | |
| "eos_token_id": 2, | |
| "feat_extract_activation": "gelu", | |
| "feat_extract_norm": "group", | |
| "feat_proj_dropout": 0.04, | |
| "feat_quantizer_dropout": 0.0, | |
| "final_dropout": 0.1, | |
| "gradient_checkpointing": true, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.047, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "layerdrop": 0.041, | |
| "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": 0.4, | |
| "model_type": "wav2vec2", | |
| "num_adapter_layers": 3, | |
| "num_attention_heads": 12, | |
| "num_codevector_groups": 2, | |
| "num_codevectors_per_group": 320, | |
| "num_conv_pos_embedding_groups": 16, | |
| "num_conv_pos_embeddings": 128, | |
| "num_feat_extract_layers": 7, | |
| "num_hidden_layers": 12, | |
| "num_negatives": 100, | |
| "output_hidden_size": 768, | |
| "pad_token_id": 39, | |
| "proj_codevector_dim": 256, | |
| "tdnn_dilation": [ | |
| 1, | |
| 2, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "tdnn_dim": [ | |
| 512, | |
| 512, | |
| 512, | |
| 512, | |
| 1500 | |
| ], | |
| "tdnn_kernel": [ | |
| 5, | |
| 3, | |
| 3, | |
| 1, | |
| 1 | |
| ], | |
| "transformers_version": "4.17.0.dev0", | |
| "use_weighted_layer_sum": false, | |
| "vocab_size": 40, | |
| "xvector_output_dim": 512 | |
| } | |
| loading feature extractor configuration file https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv/resolve/main/preprocessor_config.json from cache at /home/cahya/.cache/huggingface/transformers/34433162acde7e1ca4a265d8ae309442e4ddadff37e6e37d2d37eb7133f65f8f.fcd266b775b7f33ba9b607a0fee7cc615aeb2eb281586f046280492ea380ae23 | |
| Feature extractor Wav2Vec2FeatureExtractor { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |
| loading weights file https://huggingface.co/cahya/wav2vec2-base-turkish-artificial-cv/resolve/main/pytorch_model.bin from cache at /home/cahya/.cache/huggingface/transformers/3b3f7d0041c2b08b031c8357e39249bdbc06c8bfcd5a9f8891c7f259b07a0b85.356b4eec0d55a5c4d2d480c2dd2ea2cc0c867771bc39b8cdc97b629e4206482c | |
| Traceback (most recent call last): | |
| File "run_speech_recognition_ctc.py", line 745, in <module> | |
| main() | |
| File "run_speech_recognition_ctc.py", line 552, in main | |
| model = AutoModelForCTC.from_pretrained( | |
| File "/home/cahya/Work/MachineLearning/transformers/src/transformers/models/auto/auto_factory.py", line 447, in from_pretrained | |
| return model_class.from_pretrained(pretrained_model_name_or_path, *model_args, config=config, **kwargs) | |
| File "/home/cahya/Work/MachineLearning/transformers/src/transformers/modeling_utils.py", line 1528, in from_pretrained | |
| model, missing_keys, unexpected_keys, mismatched_keys, error_msgs = cls._load_state_dict_into_model( | |
| File "/home/cahya/Work/MachineLearning/transformers/src/transformers/modeling_utils.py", line 1682, in _load_state_dict_into_model | |
| raise RuntimeError(f"Error(s) in loading state_dict for {model.__class__.__name__}:\n\t{error_msg}") | |
| RuntimeError: Error(s) in loading state_dict for Wav2Vec2ForCTC: | |
| size mismatch for lm_head.weight: copying a param with shape torch.Size([40, 768]) from checkpoint, the shape in current model is torch.Size([41, 768]). | |
| size mismatch for lm_head.bias: copying a param with shape torch.Size([40]) from checkpoint, the shape in current model is torch.Size([41]). | |