Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 3653, "</s>": 3654}

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 3652,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 3655,
+  "xvector_output_dim": 512
+}

nohup.out

@@ -0,0 +1,800 @@
+02/06/2022 16:31:57 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True
+02/06/2022 16:31:57 - INFO - __main__ - Training/evaluation parameters TrainingArguments(
+_n_gpu=1,
+adafactor=False,
+adam_beta1=0.9,
+adam_beta2=0.999,
+adam_epsilon=1e-08,
+bf16=False,
+bf16_full_eval=False,
+dataloader_drop_last=False,
+dataloader_num_workers=0,
+dataloader_pin_memory=True,
+ddp_bucket_cap_mb=None,
+ddp_find_unused_parameters=None,
+debug=[],
+deepspeed=None,
+disable_tqdm=False,
+do_eval=True,
+do_predict=False,
+do_train=True,
+eval_accumulation_steps=None,
+eval_steps=500,
+evaluation_strategy=IntervalStrategy.STEPS,
+fp16=True,
+fp16_backend=auto,
+fp16_full_eval=False,
+fp16_opt_level=O1,
+gradient_accumulation_steps=4,
+gradient_checkpointing=True,
+greater_is_better=None,
+group_by_length=True,
+half_precision_backend=auto,
+hub_model_id=None,
+hub_strategy=HubStrategy.EVERY_SAVE,
+hub_token=<HUB_TOKEN>,
+ignore_data_skip=False,
+label_names=None,
+label_smoothing_factor=0.0,
+learning_rate=0.0001,
+length_column_name=input_length,
+load_best_model_at_end=False,
+local_rank=-1,
+log_level=-1,
+log_level_replica=-1,
+log_on_each_node=True,
+logging_dir=./runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c,
+logging_first_step=False,
+logging_nan_inf_filter=True,
+logging_steps=100,
+logging_strategy=IntervalStrategy.STEPS,
+lr_scheduler_type=SchedulerType.LINEAR,
+max_grad_norm=1.0,
+max_steps=-1,
+metric_for_best_model=None,
+mp_parameters=,
+no_cuda=False,
+num_train_epochs=100.0,
+optim=OptimizerNames.ADAMW_HF,
+output_dir=./,
+overwrite_output_dir=True,
+past_index=-1,
+per_device_eval_batch_size=8,
+per_device_train_batch_size=8,
+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>,
+remove_unused_columns=True,
+report_to=['tensorboard'],
+resume_from_checkpoint=None,
+run_name=./,
+save_on_each_node=False,
+save_steps=500,
+save_strategy=IntervalStrategy.STEPS,
+save_total_limit=3,
+seed=42,
+sharded_ddp=[],
+skip_memory_metrics=True,
+tf32=None,
+tpu_metrics_debug=False,
+tpu_num_cores=None,
+use_legacy_prediction_loop=False,
+warmup_ratio=0.0,
+warmup_steps=2000,
+weight_decay=0.0,
+xpu_backend=None,
+)
+02/06/2022 16:31:57 - WARNING - datasets.builder - Reusing dataset common_voice (/workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd)
+02/06/2022 16:31:58 - WARNING - datasets.builder - Reusing dataset common_voice (/workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd)
+02/06/2022 16:31:58 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-4b9c7ee298793a4a.arrow
+02/06/2022 16:31:58 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-229158ba70a553cf.arrow
+loading configuration file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/dabc27df63e37bd2a7a221c7774e35f36a280fbdf917cf54cadfc7df8c786f6f.a3e4c3c967d9985881e0ae550a5f6f668f897db5ab2e0802f9b97973b15970e6
+Model config Wav2Vec2Config {
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}
+
+
  0%|          | 0/1 [00:00<?, ?ba/s]
+
  0%|          | 0/1 [00:00<?, ?ba/s]
+Didn't find file ./tokenizer_config.json. We won't load it.
+Didn't find file ./added_tokens.json. We won't load it.
+Didn't find file ./special_tokens_map.json. We won't load it.
+Didn't find file ./tokenizer.json. We won't load it.
+loading file ./vocab.json
+loading file None
+loading file None
+loading file None
+loading file None
+file ./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/facebook/wav2vec2-xls-r-300m/resolve/main/config.json from cache at /workspace/.cache/huggingface/transformers/dabc27df63e37bd2a7a221c7774e35f36a280fbdf917cf54cadfc7df8c786f6f.a3e4c3c967d9985881e0ae550a5f6f668f897db5ab2e0802f9b97973b15970e6
+Model config Wav2Vec2Config {
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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": 0.075,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}
+
+loading feature extractor configuration file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/preprocessor_config.json from cache at /workspace/.cache/huggingface/transformers/6fb028b95b394059e7d3b367bbca2382b576c66aebe896f04d2cd34e1b575f5b.d4484dc1c81456a2461485e7168b04347a7b9a4e3b1ef3aba723323b33e12326
+Feature extractor Wav2Vec2FeatureExtractor {
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}
+
+loading weights file https://huggingface.co/facebook/wav2vec2-xls-r-300m/resolve/main/pytorch_model.bin from cache at /workspace/.cache/huggingface/transformers/1e6a6507f3b689035cd4b247e2a37c154e27f39143f31357a49b4e38baeccc36.1edb32803799e27ed554eb7dd935f6745b1a0b17b0ea256442fe24db6eb546cd
+Some weights of the model checkpoint at facebook/wav2vec2-xls-r-300m were not used when initializing Wav2Vec2ForCTC: ['project_hid.bias', 'quantizer.codevectors', 'quantizer.weight_proj.weight', 'project_q.weight', 'project_hid.weight', 'project_q.bias', 'quantizer.weight_proj.bias']
+- This IS expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing Wav2Vec2ForCTC from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+Some weights of Wav2Vec2ForCTC were not initialized from the model checkpoint at facebook/wav2vec2-xls-r-300m and are newly initialized: ['lm_head.weight', 'lm_head.bias']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+02/06/2022 16:32:04 - WARNING - datasets.arrow_dataset - Loading cached processed dataset at /workspace/.cache/huggingface/datasets/common_voice/zh-HK/6.1.0/5693bfc0feeade582a78c2fb250bc88f52bd86f0a7f1bb22bfee67e715de30fd/cache-34b3c26b7a1907b4.arrow
+
+
+
  0%|          | 0/3 [00:00<?, ?ba/s]
+Configuration saved in ./preprocessor_config.json
+tokenizer config file saved in ./tokenizer_config.json
+Special tokens file saved in ./special_tokens_map.json
+added tokens file saved in ./added_tokens.json
+Configuration saved in ./config.json
+loading feature extractor configuration file ./preprocessor_config.json
+loading configuration file ./config.json
+Model config Wav2Vec2Config {
+  "_name_or_path": "./",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 3652,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 3655,
+  "xvector_output_dim": 512
+}
+
+loading feature extractor configuration file ./preprocessor_config.json
+Feature extractor Wav2Vec2FeatureExtractor {
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}
+
+Didn't find file ./tokenizer.json. We won't load it.
+loading file ./vocab.json
+loading file ./tokenizer_config.json
+loading file ./added_tokens.json
+loading file ./special_tokens_map.json
+loading file None
+Adding <s> to the vocabulary
+Adding </s> to the vocabulary
+/workspace/wav2vec2-xls-r-300m-zh-HK-v2/./ is already a clone of https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2. Make sure you pull the latest changes with `repo.git_pull()`.
+02/06/2022 16:32:48 - WARNING - huggingface_hub.repository - /workspace/wav2vec2-xls-r-300m-zh-HK-v2/./ is already a clone of https://huggingface.co/w11wo/wav2vec2-xls-r-300m-zh-HK-v2. Make sure you pull the latest changes with `repo.git_pull()`.
+Using amp half precision backend
+The following columns in the training set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+/opt/conda/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use thePyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
+  warnings.warn(
+***** Running training *****
+  Num examples = 11949
+  Num Epochs = 100
+  Instantaneous batch size per device = 8
+  Total train batch size (w. parallel, distributed & accumulation) = 32
+  Gradient Accumulation steps = 4
+  Total optimization steps = 37300
+
  0%|          | 0/37300 [00:00<?, ?it/s]
  0%|          | 1/37300 [00:02<27:52:51,  2.69s/it]
  0%|          | 2/37300 [00:05<27:44:40,  2.68s/it]
  0%|          | 3/37300 [00:07<26:20:20,  2.54s/it]
  0%|          | 4/37300 [00:10<25:14:13,  2.44s/it]
  0%|          | 5/37300 [00:12<24:34:00,  2.37s/it]
  0%|          | 6/37300 [00:14<23:51:17,  2.30s/it]
  0%|          | 7/37300 [00:16<23:12:30,  2.24s/it]
  0%|          | 8/37300 [00:18<22:34:15,  2.18s/it]
  0%|          | 9/37300 [00:20<21:43:40,  2.10s/it]
  0%|          | 10/37300 [00:22<21:09:24,  2.04s/it]
  0%|          | 11/37300 [00:24<20:23:14,  1.97s/it]
  0%|          | 12/37300 [00:26<19:48:38,  1.91s/it]
  0%|          | 13/37300 [00:27<19:19:05,  1.87s/it]
  0%|          | 14/37300 [00:29<18:58:02,  1.83s/it]
  0%|          | 15/37300 [00:31<18:35:09,  1.79s/it]
  0%|          | 16/37300 [00:32<18:20:58,  1.77s/it]
  0%|          | 17/37300 [00:34<18:01:00,  1.74s/it]
  0%|          | 18/37300 [00:36<17:45:52,  1.72s/it]
  0%|          | 19/37300 [00:37<17:25:44,  1.68s/it]
  0%|          | 20/37300 [00:39<17:09:19,  1.66s/it]
  0%|          | 21/37300 [00:41<16:53:34,  1.63s/it]
  0%|          | 22/37300 [00:42<16:33:49,  1.60s/it]
  0%|          | 23/37300 [00:44<16:24:45,  1.59s/it]
  0%|          | 24/37300 [00:45<16:23:26,  1.58s/it]
  0%|          | 25/37300 [00:47<16:09:47,  1.56s/it]
  0%|          | 26/37300 [00:48<15:54:32,  1.54s/it]
  0%|          | 27/37300 [00:50<15:33:01,  1.50s/it]
  0%|          | 28/37300 [00:51<15:34:21,  1.50s/it]
  0%|          | 29/37300 [00:53<15:14:30,  1.47s/it]
  0%|          | 30/37300 [00:54<14:53:39,  1.44s/it]
  0%|          | 31/37300 [00:55<14:28:05,  1.40s/it]
  0%|          | 32/37300 [00:56<14:10:28,  1.37s/it]
  0%|          | 33/37300 [00:58<13:55:51,  1.35s/it]
  0%|          | 34/37300 [00:59<13:37:37,  1.32s/it]
  0%|          | 35/37300 [01:00<13:25:49,  1.30s/it]
  0%|          | 36/37300 [01:01<13:05:22,  1.26s/it]
  0%|          | 37/37300 [01:03<12:58:00,  1.25s/it]
  0%|          | 38/37300 [01:04<12:54:34,  1.25s/it]
  0%|          | 39/37300 [01:05<12:45:42,  1.23s/it]
  0%|          | 40/37300 [01:06<12:35:43,  1.22s/it]
  0%|          | 41/37300 [01:07<12:29:24,  1.21s/it]
  0%|          | 42/37300 [01:09<12:24:22,  1.20s/it]
  0%|          | 43/37300 [01:10<12:09:58,  1.18s/it]
  0%|          | 44/37300 [01:11<11:54:30,  1.15s/it]
  0%|          | 45/37300 [01:12<11:37:04,  1.12s/it]
  0%|          | 46/37300 [01:13<11:22:02,  1.10s/it]
  0%|          | 47/37300 [01:14<11:10:26,  1.08s/it]
  0%|          | 48/37300 [01:15<10:59:46,  1.06s/it]
  0%|          | 49/37300 [01:16<10:45:22,  1.04s/it]
  0%|          | 50/37300 [01:17<10:30:56,  1.02s/it]
  0%|          | 51/37300 [01:20<15:17:02,  1.48s/it]
  0%|          | 52/37300 [01:22<18:47:59,  1.82s/it]
  0%|          | 53/37300 [01:25<20:33:46,  1.99s/it]
  0%|          | 54/37300 [01:27<21:31:50,  2.08s/it]
  0%|          | 55/37300 [01:29<21:58:23,  2.12s/it]
  0%|          | 56/37300 [01:31<22:08:50,  2.14s/it]
  0%|          | 57/37300 [01:33<22:03:41,  2.13s/it]
  0%|          | 58/37300 [01:35<21:56:25,  2.12s/it]
  0%|          | 59/37300 [01:38<21:45:05,  2.10s/it]
  0%|          | 60/37300 [01:39<21:12:29,  2.05s/it]
  0%|          | 61/37300 [01:41<20:39:19,  2.00s/it]
  0%|          | 62/37300 [01:43<20:08:46,  1.95s/it]
  0%|          | 63/37300 [01:45<19:34:13,  1.89s/it]
  0%|          | 64/37300 [01:47<19:05:14,  1.85s/it]
  0%|          | 65/37300 [01:48<18:38:25,  1.80s/it]
  0%|          | 66/37300 [01:50<18:18:23,  1.77s/it]
  0%|          | 67/37300 [01:52<17:59:04,  1.74s/it]
  0%|          | 68/37300 [01:53<17:39:44,  1.71s/it]
  0%|          | 69/37300 [01:55<17:23:14,  1.68s/it]
  0%|          | 70/37300 [01:57<17:14:44,  1.67s/it]
  0%|          | 71/37300 [01:58<16:47:48,  1.62s/it]
  0%|          | 72/37300 [02:00<16:31:57,  1.60s/it]
  0%|          | 73/37300 [02:01<16:13:28,  1.57s/it]
  0%|          | 74/37300 [02:03<16:03:25,  1.55s/it]
  0%|          | 75/37300 [02:04<15:45:47,  1.52s/it]
  0%|          | 76/37300 [02:06<15:34:44,  1.51s/it]
  0%|          | 77/37300 [02:07<15:33:55,  1.51s/it]
  0%|          | 78/37300 [02:09<15:20:42,  1.48s/it]
  0%|          | 79/37300 [02:10<15:07:12,  1.46s/it]
  0%|          | 80/37300 [02:11<14:56:02,  1.44s/it]
  0%|          | 81/37300 [02:13<14:43:08,  1.42s/it]
  0%|          | 82/37300 [02:14<14:20:35,  1.39s/it]
  0%|          | 83/37300 [02:15<13:58:56,  1.35s/it]
  0%|          | 84/37300 [02:17<13:46:27,  1.33s/it]
  0%|          | 85/37300 [02:18<13:32:48,  1.31s/it]
  0%|          | 86/37300 [02:19<13:15:56,  1.28s/it]
  0%|          | 87/37300 [02:20<13:06:35,  1.27s/it]
  0%|          | 88/37300 [02:22<13:08:02,  1.27s/it]
  0%|          | 89/37300 [02:23<13:17:08,  1.29s/it]
  0%|          | 90/37300 [02:24<13:10:15,  1.27s/it]
  0%|          | 91/37300 [02:25<12:51:09,  1.24s/it]
  0%|          | 92/37300 [02:26<12:38:10,  1.22s/it]
  0%|          | 93/37300 [02:28<12:31:19,  1.21s/it]
  0%|          | 94/37300 [02:29<12:20:50,  1.19s/it]
  0%|          | 95/37300 [02:30<12:04:08,  1.17s/it]
  0%|          | 96/37300 [02:31<11:58:35,  1.16s/it]
  0%|          | 97/37300 [02:32<11:51:50,  1.15s/it]
  0%|          | 98/37300 [02:33<11:57:28,  1.16s/it]
  0%|          | 99/37300 [02:34<11:27:51,  1.11s/it]
  0%|          | 100/37300 [02:35<10:59:19,  1.06s/it]
                                                      
  0%|          | 100/37300 [02:35<10:59:19,  1.06s/it]
  0%|          | 101/37300 [02:38<15:45:32,  1.53s/it]
  0%|          | 102/37300 [02:40<18:45:01,  1.81s/it]
  0%|          | 103/37300 [02:43<20:54:43,  2.02s/it]
  0%|          | 104/37300 [02:45<21:57:30,  2.13s/it]
  0%|          | 105/37300 [02:48<22:31:20,  2.18s/it]
  0%|          | 106/37300 [02:50<22:43:03,  2.20s/it]
  0%|          | 107/37300 [02:52<22:35:22,  2.19s/it]
  0%|          | 108/37300 [02:54<22:28:01,  2.17s/it]
  0%|          | 109/37300 [02:56<22:07:51,  2.14s/it]
  0%|          | 110/37300 [02:58<21:38:46,  2.10s/it]
  0%|          | 111/37300 [03:00<20:54:47,  2.02s/it]
  0%|          | 112/37300 [03:02<20:20:21,  1.97s/it]
  0%|          | 113/37300 [03:04<19:49:19,  1.92s/it]
  0%|          | 114/37300 [03:05<19:12:13,  1.86s/it]
  0%|          | 115/37300 [03:07<18:44:03,  1.81s/it]
  0%|          | 116/37300 [03:09<18:22:26,  1.78s/it]
  0%|          | 117/37300 [03:11<18:04:39,  1.75s/it]
  0%|          | 118/37300 [03:12<17:47:09,  1.72s/it]
  0%|          | 119/37300 [03:14<17:27:27,  1.69s/it]
  0%|          | 120/37300 [03:15<17:20:24,  1.68s/it]
  0%|          | 121/37300 [03:17<16:59:01,  1.64s/it]
  0%|          | 122/37300 [03:19<16:42:22,  1.62s/it]
  0%|          | 123/37300 [03:20<16:21:49,  1.58s/it]
  0%|          | 124/37300 [03:22<16:05:35,  1.56s/it]
  0%|          | 125/37300 [03:23<15:48:51,  1.53s/it]
  0%|          | 126/37300 [03:24<15:35:04,  1.51s/it]
  0%|          | 127/37300 [03:26<15:18:16,  1.48s/it]
  0%|          | 128/37300 [03:27<15:03:16,  1.46s/it]
  0%|          | 129/37300 [03:29<14:59:34,  1.45s/it]
  0%|          | 130/37300 [03:30<14:46:24,  1.43s/it]
  0%|          | 131/37300 [03:31<14:31:11,  1.41s/it]
  0%|          | 132/37300 [03:33<14:15:12,  1.38s/it]
  0%|          | 133/37300 [03:34<13:58:47,  1.35s/it]
  0%|          | 134/37300 [03:35<13:42:15,  1.33s/it]
  0%|          | 135/37300 [03:37<13:30:43,  1.31s/it]
  0%|          | 136/37300 [03:38<13:19:58,  1.29s/it]
  0%|          | 137/37300 [03:39<13:06:24,  1.27s/it]
  0%|          | 138/37300 [03:40<12:58:20,  1.26s/it]
  0%|          | 139/37300 [03:42<12:48:51,  1.24s/it]
  0%|          | 140/37300 [03:43<12:39:14,  1.23s/it]
  0%|          | 141/37300 [03:44<12:31:25,  1.21s/it]
  0%|          | 142/37300 [03:45<12:21:48,  1.20s/it]
  0%|          | 143/37300 [03:46<12:11:52,  1.18s/it]
  0%|          | 144/37300 [03:47<12:02:04,  1.17s/it]
  0%|          | 145/37300 [03:48<11:45:59,  1.14s/it]
  0%|          | 146/37300 [03:49<11:28:24,  1.11s/it]
  0%|          | 147/37300 [03:50<11:14:51,  1.09s/it]
  0%|          | 148/37300 [03:52<11:00:52,  1.07s/it]
  0%|          | 149/37300 [03:53<10:48:50,  1.05s/it]
  0%|          | 150/37300 [03:54<10:38:20,  1.03s/it]
  0%|          | 151/37300 [03:56<15:47:29,  1.53s/it]
  0%|          | 152/37300 [03:59<18:55:25,  1.83s/it]
  0%|          | 153/37300 [04:01<20:26:23,  1.98s/it]
  0%|          | 154/37300 [04:03<21:20:13,  2.07s/it]
  0%|          | 155/37300 [04:06<21:41:01,  2.10s/it]
  0%|          | 156/37300 [04:08<21:49:57,  2.12s/it]
  0%|          | 157/37300 [04:10<21:52:03,  2.12s/it]
  0%|          | 158/37300 [04:12<21:41:55,  2.10s/it]
  0%|          | 159/37300 [04:14<21:18:45,  2.07s/it]
  0%|          | 160/37300 [04:16<20:51:07,  2.02s/it]
  0%|          | 161/37300 [04:18<20:24:13,  1.98s/it]
  0%|          | 162/37300 [04:19<20:01:35,  1.94s/it]
  0%|          | 163/37300 [04:21<19:33:34,  1.90s/it]
  0%|          | 164/37300 [04:23<19:05:20,  1.85s/it]
  0%|          | 165/37300 [04:25<18:42:30,  1.81s/it]
  0%|          | 166/37300 [04:26<18:20:56,  1.78s/it]
  0%|          | 167/37300 [04:28<17:59:54,  1.74s/it]
  0%|          | 168/37300 [04:30<17:40:57,  1.71s/it]
  0%|          | 169/37300 [04:31<17:23:10,  1.69s/it]
  0%|          | 170/37300 [04:33<17:06:21,  1.66s/it]
  0%|          | 171/37300 [04:35<16:55:37,  1.64s/it]
  0%|          | 172/37300 [04:36<16:37:58,  1.61s/it]
  0%|          | 173/37300 [04:38<16:18:04,  1.58s/it]
  0%|          | 174/37300 [04:39<16:04:23,  1.56s/it]
  0%|          | 175/37300 [04:41<15:48:34,  1.53s/it]
  0%|          | 176/37300 [04:42<15:34:02,  1.51s/it]
  0%|          | 177/37300 [04:43<15:21:04,  1.49s/it]
  0%|          | 178/37300 [04:45<15:07:04,  1.47s/it]
  0%|          | 179/37300 [04:46<14:52:21,  1.44s/it]
  0%|          | 180/37300 [04:48<14:37:16,  1.42s/it]
  0%|          | 181/37300 [04:49<14:17:20,  1.39s/it]
  0%|          | 182/37300 [04:50<14:02:50,  1.36s/it]
  0%|          | 183/37300 [04:52<13:46:55,  1.34s/it]
  0%|          | 184/37300 [04:53<13:31:47,  1.31s/it]
  0%|          | 185/37300 [04:54<13:19:05,  1.29s/it]
  0%|          | 186/37300 [04:55<13:04:14,  1.27s/it]
  1%|          | 187/37300 [04:56<12:56:13,  1.25s/it]
  1%|          | 188/37300 [04:58<12:50:37,  1.25s/it]
  1%|          | 189/37300 [04:59<12:44:06,  1.24s/it]
  1%|          | 190/37300 [05:00<12:32:33,  1.22s/it]
  1%|          | 191/37300 [05:01<12:26:03,  1.21s/it]
  1%|          | 192/37300 [05:02<12:23:02,  1.20s/it]
  1%|          | 193/37300 [05:04<12:13:22,  1.19s/it]
  1%|          | 194/37300 [05:05<11:58:56,  1.16s/it]
  1%|          | 195/37300 [05:06<11:38:50,  1.13s/it]
  1%|          | 196/37300 [05:07<11:23:43,  1.11s/it]
  1%|          | 197/37300 [05:08<11:11:30,  1.09s/it]
  1%|          | 198/37300 [05:09<10:57:12,  1.06s/it]
  1%|          | 199/37300 [05:10<10:44:39,  1.04s/it]
  1%|          | 200/37300 [05:11<10:33:35,  1.02s/it]
                                                      
  1%|          | 200/37300 [05:11<10:33:35,  1.02s/it]
  1%|          | 201/37300 [05:13<15:31:47,  1.51s/it]
  1%|          | 202/37300 [05:16<18:41:01,  1.81s/it]
  1%|          | 203/37300 [05:18<20:25:35,  1.98s/it]
  1%|          | 204/37300 [05:21<21:20:46,  2.07s/it]
  1%|          | 205/37300 [05:23<21:47:59,  2.12s/it]
  1%|          | 206/37300 [05:25<21:57:05,  2.13s/it]
  1%|          | 207/37300 [05:27<21:46:58,  2.11s/it]
  1%|          | 208/37300 [05:29<21:27:39,  2.08s/it]
  1%|          | 209/37300 [05:31<21:09:13,  2.05s/it]
  1%|          | 210/37300 [05:33<20:38:21,  2.00s/it]
  1%|          | 211/37300 [05:35<20:06:57,  1.95s/it]
  1%|          | 212/37300 [05:37<19:39:36,  1.91s/it]
  1%|          | 213/37300 [05:38<19:13:12,  1.87s/it]
  1%|          | 214/37300 [05:40<18:48:22,  1.83s/it]
  1%|          | 215/37300 [05:42<18:28:07,  1.79s/it]
  1%|          | 216/37300 [05:44<18:11:30,  1.77s/it]
  1%|          | 217/37300 [05:45<17:56:19,  1.74s/it]
  1%|          | 218/37300 [05:47<17:38:08,  1.71s/it]
  1%|          | 219/37300 [05:49<17:21:49,  1.69s/it]
  1%|          | 220/37300 [05:50<17:03:17,  1.66s/it]
  1%|          | 221/37300 [05:52<16:48:03,  1.63s/it]
  1%|          | 222/37300 [05:53<16:31:37,  1.60s/it]
  1%|          | 223/37300 [05:55<16:13:34,  1.58s/it]
  1%|          | 224/37300 [05:56<15:51:53,  1.54s/it]
  1%|          | 225/37300 [05:58<15:38:33,  1.52s/it]
  1%|          | 226/37300 [05:59<15:27:25,  1.50s/it]
  1%|          | 227/37300 [06:01<15:12:26,  1.48s/it]
  1%|          | 228/37300 [06:02<14:57:47,  1.45s/it]
  1%|          | 229/37300 [06:03<14:52:51,  1.45s/it]
  1%|          | 230/37300 [06:05<14:39:29,  1.42s/it]
  1%|          | 231/37300 [06:06<14:21:08,  1.39s/it]
  1%|          | 232/37300 [06:07<14:05:47,  1.37s/it]
  1%|          | 233/37300 [06:09<13:51:04,  1.35s/it]
  1%|          | 234/37300 [06:10<13:37:55,  1.32s/it]
  1%|          | 235/37300 [06:11<13:24:52,  1.30s/it]
  1%|          | 236/37300 [06:12<13:16:21,  1.29s/it]
  1%|          | 237/37300 [06:14<13:04:33,  1.27s/it]
  1%|          | 238/37300 [06:15<12:51:23,  1.25s/it]
  1%|          | 239/37300 [06:16<12:39:44,  1.23s/it]
  1%|          | 240/37300 [06:17<12:28:34,  1.21s/it]
  1%|          | 241/37300 [06:18<12:18:29,  1.20s/it]
  1%|          | 242/37300 [06:20<12:10:01,  1.18s/it]
  1%|          | 243/37300 [06:21<11:57:15,  1.16s/it]
  1%|          | 244/37300 [06:22<11:42:43,  1.14s/it]
  1%|          | 245/37300 [06:23<11:29:25,  1.12s/it]
  1%|          | 246/37300 [06:24<11:16:00,  1.09s/it]
  1%|          | 247/37300 [06:25<11:04:52,  1.08s/it]
  1%|          | 248/37300 [06:26<10:52:38,  1.06s/it]
  1%|          | 249/37300 [06:27<10:42:50,  1.04s/it]
  1%|          | 250/37300 [06:28<10:29:23,  1.02s/it]
  1%|          | 251/37300 [06:31<15:29:58,  1.51s/it]
  1%|          | 252/37300 [06:33<18:28:44,  1.80s/it]
  1%|          | 253/37300 [06:35<20:06:55,  1.95s/it]
  1%|          | 254/37300 [06:38<21:04:00,  2.05s/it]
  1%|          | 255/37300 [06:40<21:34:26,  2.10s/it]
  1%|          | 256/37300 [06:42<21:45:33,  2.11s/it]
  1%|          | 257/37300 [06:44<21:38:14,  2.10s/it]
  1%|          | 258/37300 [06:46<21:19:51,  2.07s/it]
  1%|          | 259/37300 [06:48<20:58:49,  2.04s/it]
  1%|          | 260/37300 [06:50<20:38:07,  2.01s/it]
  1%|          | 261/37300 [06:52<20:03:34,  1.95s/it]
  1%|          | 262/37300 [06:54<19:34:28,  1.90s/it]
  1%|          | 263/37300 [06:55<19:09:15,  1.86s/it]
  1%|          | 264/37300 [06:57<18:43:50,  1.82s/it]
  1%|          | 265/37300 [06:59<18:23:06,  1.79s/it]
  1%|          | 266/37300 [07:00<18:02:27,  1.75s/it]
  1%|          | 267/37300 [07:02<17:41:46,  1.72s/it]
  1%|          | 268/37300 [07:04<17:21:27,  1.69s/it]
  1%|          | 269/37300 [07:05<17:02:20,  1.66s/it]
  1%|          | 270/37300 [07:07<16:41:34,  1.62s/it]
  1%|          | 271/37300 [07:08<16:24:24,  1.60s/it]
  1%|          | 272/37300 [07:10<16:10:44,  1.57s/it]
  1%|          | 273/37300 [07:11<15:58:13,  1.55s/it]
  1%|          | 274/37300 [07:13<15:48:52,  1.54s/it]
  1%|          | 275/37300 [07:14<15:25:32,  1.50s/it]
  1%|          | 276/37300 [07:16<15:19:58,  1.49s/it]
  1%|          | 277/37300 [07:17<15:09:44,  1.47s/it]
  1%|          | 278/37300 [07:19<14:54:52,  1.45s/it]
  1%|          | 279/37300 [07:20<14:38:45,  1.42s/it]
  1%|          | 280/37300 [07:21<14:25:20,  1.40s/it]
  1%|          | 281/37300 [07:23<14:02:50,  1.37s/it]
  1%|          | 282/37300 [07:24<13:51:04,  1.35s/it]
  1%|          | 283/37300 [07:25<13:40:56,  1.33s/it]
  1%|          | 284/37300 [07:26<13:29:15,  1.31s/it]
  1%|          | 285/37300 [07:28<13:18:39,  1.29s/it]
  1%|          | 286/37300 [07:29<13:08:10,  1.28s/it]
  1%|          | 287/37300 [07:30<12:59:39,  1.26s/it]
  1%|          | 288/37300 [07:31<12:52:29,  1.25s/it]
  1%|          | 289/37300 [07:33<12:45:20,  1.24s/it]
  1%|          | 290/37300 [07:34<12:36:16,  1.23s/it]
  1%|          | 291/37300 [07:35<12:24:28,  1.21s/it]
  1%|          | 292/37300 [07:36<12:12:44,  1.19s/it]
  1%|          | 293/37300 [07:37<11:58:28,  1.16s/it]
  1%|          | 294/37300 [07:38<11:40:55,  1.14s/it]
  1%|          | 295/37300 [07:39<11:26:52,  1.11s/it]
  1%|          | 296/37300 [07:40<11:13:02,  1.09s/it]
  1%|          | 297/37300 [07:41<11:04:15,  1.08s/it]
  1%|          | 298/37300 [07:42<11:03:23,  1.08s/it]
  1%|          | 299/37300 [07:44<11:00:40,  1.07s/it]
  1%|          | 300/37300 [07:45<10:55:45,  1.06s/it]
                                                      
  1%|          | 300/37300 [07:45<10:55:45,  1.06s/it]
  1%|          | 301/37300 [07:47<16:10:58,  1.57s/it]
  1%|          | 302/37300 [07:50<19:12:13,  1.87s/it]
  1%|          | 303/37300 [07:52<20:47:24,  2.02s/it]
  1%|          | 304/37300 [07:55<21:33:25,  2.10s/it]
  1%|          | 305/37300 [07:57<21:50:10,  2.12s/it]
  1%|          | 306/37300 [07:59<21:47:30,  2.12s/it]
  1%|          | 307/37300 [08:01<21:32:10,  2.10s/it]
  1%|          | 308/37300 [08:03<21:16:45,  2.07s/it]
  1%|          | 309/37300 [08:05<20:45:55,  2.02s/it]
  1%|          | 310/37300 [08:07<20:20:14,  1.98s/it]
  1%|          | 311/37300 [08:09<19:54:30,  1.94s/it]
  1%|          | 312/37300 [08:10<19:26:14,  1.89s/it]
  1%|          | 313/37300 [08:12<19:03:03,  1.85s/it]
  1%|          | 314/37300 [08:14<18:36:53,  1.81s/it]
  1%|          | 315/37300 [08:15<18:18:38,  1.78s/it]
  1%|          | 316/37300 [08:17<17:59:06,  1.75s/it]
  1%|          | 317/37300 [08:19<17:42:03,  1.72s/it]
  1%|          | 318/37300 [08:20<17:25:54,  1.70s/it]
  1%|          | 319/37300 [08:22<17:09:21,  1.67s/it]
  1%|          | 320/37300 [08:24<16:58:56,  1.65s/it]
  1%|          | 321/37300 [08:25<16:45:02,  1.63s/it]
  1%|          | 322/37300 [08:27<16:20:16,  1.59s/it]
  1%|          | 323/37300 [08:28<15:56:38,  1.55s/it]
  1%|          | 324/37300 [08:30<15:37:13,  1.52s/it]
  1%|          | 325/37300 [08:31<15:21:09,  1.49s/it]
  1%|          | 326/37300 [08:33<15:06:23,  1.47s/it]
  1%|          | 327/37300 [08:34<14:57:39,  1.46s/it]
  1%|          | 328/37300 [08:35<14:49:20,  1.44s/it]
  1%|          | 329/37300 [08:37<14:39:49,  1.43s/it]
  1%|          | 330/37300 [08:38<14:27:18,  1.41s/it]
  1%|          | 331/37300 [08:39<13:59:32,  1.36s/it]
  1%|          | 332/37300 [08:41<13:33:00,  1.32s/it]
  1%|          | 333/37300 [08:42<13:10:45,  1.28s/it]
  1%|          | 334/37300 [08:43<12:51:01,  1.25s/it]
  1%|          | 335/37300 [08:44<12:44:14,  1.24s/it]
  1%|          | 336/37300 [08:45<12:40:36,  1.23s/it]
  1%|          | 337/37300 [08:47<12:35:46,  1.23s/it]
  1%|          | 338/37300 [08:48<12:31:18,  1.22s/it]
  1%|          | 339/37300 [08:49<12:28:38,  1.22s/it]
  1%|          | 340/37300 [08:50<12:20:34,  1.20s/it]
  1%|          | 341/37300 [08:51<12:14:34,  1.19s/it]
  1%|          | 342/37300 [08:53<12:11:17,  1.19s/it]
  1%|          | 343/37300 [08:54<12:02:42,  1.17s/it]
  1%|          | 344/37300 [08:55<11:49:23,  1.15s/it]
  1%|          | 345/37300 [08:56<11:34:14,  1.13s/it]
  1%|          | 346/37300 [08:57<11:24:38,  1.11s/it]
  1%|          | 347/37300 [08:58<11:17:38,  1.10s/it]
  1%|          | 348/37300 [08:59<11:07:13,  1.08s/it]
  1%|          | 349/37300 [09:00<11:01:01,  1.07s/it]
  1%|          | 350/37300 [09:01<10:51:43,  1.06s/it]
  1%|          | 351/37300 [09:04<15:53:24,  1.55s/it]
  1%|          | 352/37300 [09:06<18:25:47,  1.80s/it]
  1%|          | 353/37300 [09:08<19:34:30,  1.91s/it]
  1%|          | 354/37300 [09:10<19:51:19,  1.93s/it]
  1%|          | 355/37300 [09:12<19:55:51,  1.94s/it]
  1%|          | 356/37300 [09:14<19:22:22,  1.89s/it]
  1%|          | 357/37300 [09:16<18:51:28,  1.84s/it]
  1%|          | 358/37300 [09:17<18:19:14,  1.79s/it]
  1%|          | 359/37300 [09:19<17:44:58,  1.73s/it]
  1%|          | 360/37300 [09:21<17:08:49,  1.67s/it]
  1%|          | 361/37300 [09:22<16:34:13,  1.61s/it]
  1%|          | 362/37300 [09:24<16:03:16,  1.56s/it]
  1%|          | 363/37300 [09:25<15:38:10,  1.52s/it]
  1%|          | 364/37300 [09:26<15:09:52,  1.48s/it]
  1%|          | 365/37300 [09:28<14:35:35,  1.42s/it]
  1%|          | 366/37300 [09:29<14:03:17,  1.37s/it]
  1%|          | 367/37300 [09:30<13:37:19,  1.33s/it]
  1%|          | 368/37300 [09:31<13:13:03,  1.29s/it]
  1%|          | 369/37300 [09:32<12:51:08,  1.25s/it]
  1%|          | 370/37300 [09:34<12:38:03,  1.23s/it]
  1%|          | 371/37300 [09:35<12:28:26,  1.22s/it]
  1%|          | 372/37300 [09:36<12:14:34,  1.19s/it]
  1%|          | 373/37300 [09:37<12:02:00,  1.17s/it]
  1%|          | 374/37300 [09:40<18:23:02,  1.79s/it]
  1%|          | 375/37300 [09:43<21:07:36,  2.06s/it]
  1%|          | 376/37300 [09:46<22:35:22,  2.20s/it]
  1%|          | 377/37300 [09:48<23:14:10,  2.27s/it]
  1%|          | 378/37300 [09:50<23:30:37,  2.29s/it]
  1%|          | 379/37300 [09:53<23:30:25,  2.29s/it]
  1%|          | 380/37300 [09:55<23:05:48,  2.25s/it]
  1%|          | 381/37300 [09:57<22:25:43,  2.19s/it]
  1%|          | 382/37300 [09:59<21:33:51,  2.10s/it]
  1%|          | 383/37300 [10:01<20:54:02,  2.04s/it]
  1%|          | 384/37300 [10:02<20:13:07,  1.97s/it]
  1%|          | 385/37300 [10:04<19:38:56,  1.92s/it]
  1%|          | 386/37300 [10:06<19:08:45,  1.87s/it]
  1%|          | 387/37300 [10:08<18:41:06,  1.82s/it]
  1%|          | 388/37300 [10:09<18:14:14,  1.78s/it]
  1%|          | 389/37300 [10:11<17:53:33,  1.75s/it]
  1%|          | 390/37300 [10:13<17:33:59,  1.71s/it]
  1%|          | 391/37300 [10:14<17:23:13,  1.70s/it]
  1%|          | 392/37300 [10:16<17:04:20,  1.67s/it]
  1%|          | 393/37300 [10:17<16:42:16,  1.63s/it]
  1%|          | 394/37300 [10:19<16:25:13,  1.60s/it]
  1%|          | 395/37300 [10:21<16:16:03,  1.59s/it]
  1%|          | 396/37300 [10:22<15:51:12,  1.55s/it]
  1%|          | 397/37300 [10:23<15:31:56,  1.52s/it]
  1%|          | 398/37300 [10:25<15:21:09,  1.50s/it]
  1%|          | 399/37300 [10:26<15:11:11,  1.48s/it]
  1%|          | 400/37300 [10:28<15:00:01,  1.46s/it]
                                                      
  1%|          | 400/37300 [10:28<15:00:01,  1.46s/it]
  1%|          | 401/37300 [10:29<14:47:32,  1.44s/it]
  1%|          | 402/37300 [10:31<14:38:28,  1.43s/it]
  1%|          | 403/37300 [10:32<14:24:39,  1.41s/it]
  1%|          | 404/37300 [10:33<14:03:43,  1.37s/it]
  1%|          | 405/37300 [10:34<13:52:50,  1.35s/it]
  1%|          | 406/37300 [10:36<13:39:16,  1.33s/it]
  1%|          | 407/37300 [10:37<13:23:59,  1.31s/it]
  1%|          | 408/37300 [10:38<13:13:51,  1.29s/it]
  1%|          | 409/37300 [10:39<13:00:44,  1.27s/it]
  1%|          | 410/37300 [10:41<13:07:06,  1.28s/it]
  1%|          | 411/37300 [10:42<13:04:49,  1.28s/it]
  1%|          | 412/37300 [10:43<12:59:21,  1.27s/it]
  1%|          | 413/37300 [10:45<12:54:01,  1.26s/it]
  1%|          | 414/37300 [10:46<12:36:07,  1.23s/it]
  1%|          | 415/37300 [10:47<12:23:33,  1.21s/it]
  1%|          | 416/37300 [10:48<12:13:15,  1.19s/it]
  1%|          | 417/37300 [10:49<11:52:20,  1.16s/it]
  1%|          | 418/37300 [10:50<11:43:37,  1.14s/it]
  1%|          | 419/37300 [10:51<11:26:02,  1.12s/it]
  1%|          | 420/37300 [10:52<11:09:22,  1.09s/it]
  1%|          | 421/37300 [10:53<10:54:00,  1.06s/it]
  1%|          | 422/37300 [10:54<10:38:28,  1.04s/it]
  1%|          | 423/37300 [10:55<10:23:41,  1.01s/it]
  1%|          | 424/37300 [10:58<15:23:42,  1.50s/it]
  1%|          | 425/37300 [11:00<18:33:47,  1.81s/it]
  1%|          | 426/37300 [11:03<20:13:15,  1.97s/it]
  1%|          | 427/37300 [11:05<21:18:42,  2.08s/it]
  1%|          | 428/37300 [11:07<21:46:07,  2.13s/it]
  1%|          | 429/37300 [11:09<21:49:41,  2.13s/it]
  1%|          | 430/37300 [11:12<21:44:41,  2.12s/it]
  1%|          | 431/37300 [11:14<21:30:55,  2.10s/it]
  1%|          | 432/37300 [11:16<21:14:23,  2.07s/it]
  1%|          | 433/37300 [11:18<20:43:34,  2.02s/it]
  1%|          | 434/37300 [11:19<20:18:57,  1.98s/it]
  1%|          | 435/37300 [11:21<19:47:27,  1.93s/it]
  1%|          | 436/37300 [11:23<19:22:53,  1.89s/it]
  1%|          | 437/37300 [11:25<19:00:48,  1.86s/it]
  1%|          | 438/37300 [11:27<18:51:44,  1.84s/it]
  1%|          | 439/37300 [11:28<18:27:19,  1.80s/it]
  1%|          | 440/37300 [11:30<18:08:23,  1.77s/it]
  1%|          | 441/37300 [11:32<17:47:58,  1.74s/it]
  1%|          | 442/37300 [11:33<17:31:46,  1.71s/it]
  1%|          | 443/37300 [11:35<17:14:11,  1.68s/it]
  1%|          | 444/37300 [11:37<16:54:51,  1.65s/it]
  1%|          | 445/37300 [11:38<16:40:53,  1.63s/it]
  1%|          | 446/37300 [11:40<16:22:57,  1.60s/it]
  1%|          | 447/37300 [11:41<16:05:18,  1.57s/it]
  1%|          | 448/37300 [11:43<15:49:17,  1.55s/it]
  1%|          | 449/37300 [11:44<15:38:40,  1.53s/it]
  1%|          | 450/37300 [11:46<15:24:17,  1.50s/it]
  1%|          | 451/37300 [11:47<15:09:51,  1.48s/it]
  1%|          | 452/37300 [11:48<14:56:31,  1.46s/it]
  1%|          | 453/37300 [11:50<14:41:32,  1.44s/it]
  1%|          | 454/37300 [11:51<14:31:58,  1.42s/it]
  1%|          | 455/37300 [11:52<14:12:11,  1.39s/it]
  1%|          | 456/37300 [11:54<13:56:00,  1.36s/it]
  1%|          | 457/37300 [11:55<13:37:46,  1.33s/it]
  1%|          | 458/37300 [11:56<13:19:43,  1.30s/it]
  1%|          | 459/37300 [11:58<13:08:43,  1.28s/it]
  1%|          | 460/37300 [11:59<12:55:34,  1.26s/it]
  1%|          | 461/37300 [12:00<12:50:36,  1.26s/it]
  1%|          | 462/37300 [12:01<12:42:06,  1.24s/it]
  1%|          | 463/37300 [12:02<12:31:09,  1.22s/it]
  1%|          | 464/37300 [12:04<12:19:40,  1.20s/it]
  1%|          | 465/37300 [12:05<12:09:04,  1.19s/it]
  1%|          | 466/37300 [12:06<11:57:00,  1.17s/it]
  1%|▏         | 467/37300 [12:07<11:40:36,  1.14s/it]
  1%|▏         | 468/37300 [12:08<11:26:55,  1.12s/it]
  1%|▏         | 469/37300 [12:09<11:13:20,  1.10s/it]
  1%|▏         | 470/37300 [12:10<11:00:30,  1.08s/it]
  1%|▏         | 471/37300 [12:11<10:49:08,  1.06s/it]
  1%|▏         | 472/37300 [12:12<10:36:47,  1.04s/it]
  1%|▏         | 473/37300 [12:13<10:23:46,  1.02s/it]
  1%|▏         | 474/37300 [12:16<15:07:13,  1.48s/it]
  1%|▏         | 475/37300 [12:18<18:21:41,  1.80s/it]
  1%|▏         | 476/37300 [12:20<20:09:53,  1.97s/it]
  1%|▏         | 477/37300 [12:23<21:01:58,  2.06s/it]
  1%|▏         | 478/37300 [12:25<21:27:36,  2.10s/it]
  1%|▏         | 479/37300 [12:27<21:35:40,  2.11s/it]
  1%|▏         | 480/37300 [12:29<21:23:24,  2.09s/it]
  1%|▏         | 481/37300 [12:31<21:10:37,  2.07s/it]
  1%|▏         | 482/37300 [12:33<20:46:29,  2.03s/it]
  1%|▏         | 483/37300 [12:35<20:20:44,  1.99s/it]
  1%|▏         | 484/37300 [12:37<19:52:00,  1.94s/it]
  1%|▏         | 485/37300 [12:39<19:23:01,  1.90s/it]
  1%|▏         | 486/37300 [12:40<19:02:47,  1.86s/it]
  1%|▏         | 487/37300 [12:42<18:35:06,  1.82s/it]
  1%|▏         | 488/37300 [12:44<18:10:05,  1.78s/it]
  1%|▏         | 489/37300 [12:45<17:56:05,  1.75s/it]
  1%|▏         | 490/37300 [12:47<17:39:09,  1.73s/it]
  1%|▏         | 491/37300 [12:49<17:27:46,  1.71s/it]
  1%|▏         | 492/37300 [12:50<17:15:08,  1.69s/it]
  1%|▏         | 493/37300 [12:52<16:57:58,  1.66s/it]
  1%|▏         | 494/37300 [12:54<16:42:08,  1.63s/it]
  1%|▏         | 495/37300 [12:55<16:29:22,  1.61s/it]
  1%|▏         | 496/37300 [12:57<16:13:01,  1.59s/it]
  1%|▏         | 497/37300 [12:58<15:59:08,  1.56s/it]
  1%|▏         | 498/37300 [13:00<15:37:34,  1.53s/it]
  1%|▏         | 499/37300 [13:01<15:14:28,  1.49s/it]
  1%|▏         | 500/37300 [13:02<14:56:05,  1.46s/it]
                                                      
  1%|▏         | 500/37300 [13:02<14:56:05,  1.46s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 2302
+  Batch size = 8
+{'loss': 153.5094, 'learning_rate': 4.85e-06, 'epoch': 0.27}
+{'loss': 108.8648, 'learning_rate': 9.85e-06, 'epoch': 0.54}
+{'loss': 92.5714, 'learning_rate': 1.48e-05, 'epoch': 0.8}
+{'loss': 79.9356, 'learning_rate': 1.9800000000000004e-05, 'epoch': 1.07}
+{'loss': 69.8341, 'learning_rate': 2.48e-05, 'epoch': 1.34}
+
+
  0%|          | 0/288 [00:00<?, ?it/s]
+
  1%|          | 2/288 [00:00<00:39,  7.26it/s]
+
  1%|          | 3/288 [00:00<01:06,  4.26it/s]
+
  1%|▏         | 4/288 [00:00<01:15,  3.75it/s]
+
  2%|▏         | 5/288 [00:01<01:13,  3.84it/s]
+
  2%|▏         | 6/288 [00:01<01:15,  3.74it/s]
+
  2%|▏         | 7/288 [00:01<01:18,  3.57it/s]
+
  3%|▎         | 8/288 [00:02<01:15,  3.72it/s]
+
  3%|▎         | 9/288 [00:02<01:19,  3.53it/s]
+
  3%|▎         | 10/288 [00:02<01:27,  3.17it/s]
+
  4%|▍         | 11/288 [00:03<01:29,  3.10it/s]
+
  4%|▍         | 12/288 [00:03<01:24,  3.28it/s]
+
  5%|▍         | 13/288 [00:03<01:25,  3.21it/s]
+
  5%|▍         | 14/288 [00:03<01:24,  3.23it/s]
+
  5%|▌         | 15/288 [00:04<01:21,  3.36it/s]
+
  6%|▌         | 16/288 [00:04<01:22,  3.30it/s]
+
  6%|▌         | 17/288 [00:04<01:21,  3.34it/s]
+
  6%|▋         | 18/288 [00:05<01:23,  3.21it/s]
+
  7%|▋         | 19/288 [00:05<01:26,  3.12it/s]
+
  7%|▋         | 20/288 [00:05<01:23,  3.21it/s]
+
  7%|▋         | 21/288 [00:06<01:22,  3.24it/s]
+
  8%|▊         | 22/288 [00:06<01:20,  3.30it/s]
+
  8%|▊         | 23/288 [00:06<01:22,  3.20it/s]
+
  8%|▊         | 24/288 [00:07<01:24,  3.12it/s]
+
  9%|▊         | 25/288 [00:07<01:23,  3.15it/s]
+
  9%|▉         | 26/288 [00:07<01:27,  2.99it/s]
+
  9%|▉         | 27/288 [00:08<01:26,  3.01it/s]
+
 10%|▉         | 28/288 [00:08<01:23,  3.11it/s]
+
 10%|█         | 29/288 [00:08<01:19,  3.26it/s]
+
 10%|█         | 30/288 [00:08<01:11,  3.60it/s]
+
 11%|█         | 31/288 [00:09<01:10,  3.66it/s]
+
 11%|█         | 32/288 [00:09<01:12,  3.52it/s]
+
 11%|█▏        | 33/288 [00:09<01:10,  3.62it/s]
+
 12%|█▏        | 34/288 [00:10<01:11,  3.55it/s]
+
 12%|█▏        | 35/288 [00:10<01:12,  3.48it/s]
+
 12%|█▎        | 36/288 [00:10<01:14,  3.40it/s]
+
 13%|█▎        | 37/288 [00:10<01:13,  3.40it/s]
+
 13%|█▎        | 38/288 [00:11<01:13,  3.41it/s]
+
 14%|█▎        | 39/288 [00:11<01:14,  3.34it/s]
+
 14%|█▍        | 40/288 [00:11<01:17,  3.19it/s]
+
 14%|█▍        | 41/288 [00:12<01:15,  3.26it/s]
+
 15%|█▍        | 42/288 [00:12<01:17,  3.16it/s]
+
 15%|█▍        | 43/288 [00:12<01:18,  3.11it/s]
+
 15%|█▌        | 44/288 [00:13<01:17,  3.15it/s]
+
 16%|█▌        | 45/288 [00:13<01:17,  3.13it/s]
+
 16%|█▌        | 46/288 [00:13<01:16,  3.16it/s]
+
 16%|█▋        | 47/288 [00:14<01:20,  3.01it/s]
+
 17%|█▋        | 48/288 [00:14<01:24,  2.85it/s]
+
 17%|█▋        | 49/288 [00:14<01:20,  2.96it/s]
+
 17%|█▋        | 50/288 [00:15<01:18,  3.05it/s]
+
 18%|█▊        | 51/288 [00:15<01:16,  3.08it/s]
+
 18%|█▊        | 52/288 [00:15<01:19,  2.95it/s]
+
 18%|█▊        | 53/288 [00:16<01:21,  2.88it/s]
+
 19%|█▉        | 54/288 [00:16<01:19,  2.95it/s]
+
 19%|█▉        | 55/288 [00:16<01:22,  2.84it/s]
+
 19%|█▉        | 56/288 [00:17<01:19,  2.91it/s]
+
 20%|█▉        | 57/288 [00:17<01:15,  3.08it/s]
+
 20%|██        | 58/288 [00:17<01:10,  3.24it/s]
+
 20%|██        | 59/288 [00:18<01:07,  3.37it/s]
+
 21%|██        | 60/288 [00:18<01:04,  3.56it/s]
+
 21%|██        | 61/288 [00:18<01:08,  3.33it/s]
+
 22%|██▏       | 62/288 [00:18<01:08,  3.28it/s]
+
 22%|██▏       | 63/288 [00:19<01:09,  3.23it/s]
+
 22%|██▏       | 64/288 [00:19<01:07,  3.32it/s]
+
 23%|██▎       | 65/288 [00:19<01:10,  3.17it/s]
+
 23%|██▎       | 66/288 [00:20<01:11,  3.10it/s]
+
 23%|██▎       | 67/288 [00:20<01:09,  3.16it/s]
+
 24%|██▎       | 68/288 [00:20<01:11,  3.09it/s]
+
 24%|██▍       | 69/288 [00:21<01:12,  3.04it/s]
+
 24%|██▍       | 70/288 [00:21<01:10,  3.07it/s]
+
 25%|██▍       | 71/288 [00:21<01:13,  2.95it/s]
+
 25%|██▌       | 72/288 [00:22<01:16,  2.84it/s]
+
 25%|██▌       | 73/288 [00:22<01:14,  2.89it/s]
+
 26%|██▌       | 74/288 [00:22<01:14,  2.88it/s]
+
 26%|██▌       | 75/288 [00:23<01:14,  2.87it/s]
+
 26%|██▋       | 76/288 [00:23<01:10,  2.99it/s]
+
 27%|██▋       | 77/288 [00:23<01:10,  2.98it/s]
+
 27%|██▋       | 78/288 [00:24<01:09,  3.04it/s]
+
 27%|██▋       | 79/288 [00:24<01:07,  3.11it/s]
+
 28%|██▊       | 80/288 [00:24<01:05,  3.20it/s]
+
 28%|██▊       | 81/288 [00:25<01:07,  3.06it/s]
+
 28%|██▊       | 82/288 [00:25<01:05,  3.13it/s]
+
 29%|██▉       | 83/288 [00:25<01:05,  3.13it/s]
+
 29%|██▉       | 84/288 [00:26<01:00,  3.39it/s]
+
 30%|██▉       | 85/288 [00:26<00:58,  3.44it/s]
+
 30%|██▉       | 86/288 [00:26<01:02,  3.24it/s]
+
 30%|███       | 87/288 [00:27<01:07,  2.99it/s]
+
 31%|███       | 88/288 [00:27<01:06,  2.99it/s]
+
 31%|███       | 89/288 [00:27<01:04,  3.09it/s]
+
 31%|███▏      | 90/288 [00:28<01:02,  3.17it/s]
+
 32%|███▏      | 91/288 [00:28<01:03,  3.12it/s]
+
 32%|███▏      | 92/288 [00:28<01:02,  3.15it/s]
+
 32%|███▏      | 93/288 [00:29<01:03,  3.06it/s]
+
 33%|███▎      | 94/288 [00:29<01:02,  3.09it/s]
+
 33%|███▎      | 95/288 [00:29<01:02,  3.08it/s]
+
 33%|███▎      | 96/288 [00:29<00:58,  3.26it/s]
+
 34%|███▎      | 97/288 [00:30<00:56,  3.36it/s]
+
 34%|███▍      | 98/288 [00:30<00:58,  3.24it/s]
+
 34%|███▍      | 99/288 [00:30<01:00,  3.11it/s]
+
 35%|███▍      | 100/288 [00:31<01:05,  2.87it/s]
+
 35%|███▌      | 101/288 [00:31<01:03,  2.97it/s]
+
 35%|███▌      | 102/288 [00:31<00:59,  3.11it/s]
+
 36%|███▌      | 103/288 [00:32<00:58,  3.17it/s]
+
 36%|███▌      | 104/288 [00:32<00:58,  3.13it/s]
+
 36%|███▋      | 105/288 [00:32<00:55,  3.31it/s]
+
 37%|███▋      | 106/288 [00:33<00:57,  3.16it/s]
+
 37%|███▋      | 107/288 [00:33<00:57,  3.15it/s]
+
 38%|███▊      | 108/288 [00:33<00:57,  3.13it/s]
+
 38%|███▊      | 109/288 [00:34<00:57,  3.11it/s]
+
 38%|███▊      | 110/288 [00:34<00:56,  3.15it/s]
+
 39%|███▊      | 111/288 [00:34<01:02,  2.82it/s]
+
 39%|███▉      | 112/288 [00:35<01:01,  2.85it/s]
+
 39%|███▉      | 113/288 [00:35<00:59,  2.93it/s]
+
 40%|███▉      | 114/288 [00:35<00:58,  2.96it/s]
+
 40%|███▉      | 115/288 [00:36<00:56,  3.06it/s]
+
 40%|████      | 116/288 [00:36<00:56,  3.02it/s]
+
 41%|████      | 117/288 [00:36<00:55,  3.06it/s]
+
 41%|████      | 118/288 [00:37<00:52,  3.23it/s]
+
 41%|████▏     | 119/288 [00:37<00:53,  3.13it/s]
+
 42%|████▏     | 120/288 [00:37<01:00,  2.78it/s]
+
 42%|████▏     | 121/288 [00:38<00:56,  2.94it/s]
+
 42%|████▏     | 122/288 [00:38<00:51,  3.20it/s]
+
 43%|████▎     | 123/288 [00:38<00:54,  3.05it/s]
+
 43%|████▎     | 124/288 [00:39<00:53,  3.07it/s]
+
 43%|████▎     | 125/288 [00:39<00:52,  3.10it/s]
+
 44%|████▍     | 126/288 [00:39<00:54,  2.99it/s]
+
 44%|████▍     | 127/288 [00:40<00:52,  3.07it/s]
+
 44%|████▍     | 128/288 [00:40<00:51,  3.08it/s]
+
 45%|████▍     | 129/288 [00:41<01:05,  2.41it/s]
+
 45%|████▌     | 130/288 [00:41<01:01,  2.56it/s]
+
 45%|████▌     | 131/288 [00:41<00:57,  2.75it/s]
+
 46%|████▌     | 132/288 [00:42<00:55,  2.83it/s]
+
 46%|████▌     | 133/288 [00:42<00:55,  2.78it/s]
+
 47%|████▋     | 134/288 [00:42<00:55,  2.77it/s]
+
 47%|████▋     | 135/288 [00:43<00:53,  2.85it/s]
+
 47%|████▋     | 136/288 [00:43<00:51,  2.93it/s]
+
 48%|████▊     | 137/288 [00:43<01:01,  2.47it/s]
+
 48%|████▊     | 138/288 [00:44<00:58,  2.57it/s]
+
 48%|████▊     | 139/288 [00:44<00:55,  2.66it/s]
+
 49%|████▊     | 140/288 [00:45<00:53,  2.74it/s]
+
 49%|████▉     | 141/288 [00:45<00:53,  2.74it/s]
+
 49%|████▉     | 142/288 [00:45<00:50,  2.87it/s]
+
 50%|████▉     | 143/288 [00:46<00:50,  2.87it/s]
+
 50%|█████     | 144/288 [00:46<00:50,  2.85it/s]
+
 50%|█████     | 145/288 [00:46<00:49,  2.88it/s]
+
 51%|█████     | 146/288 [00:47<00:47,  3.00it/s]
+
 51%|█████     | 147/288 [00:47<00:45,  3.10it/s]
+
 51%|█████▏    | 148/288 [00:47<00:45,  3.08it/s]
+
 52%|█████▏    | 149/288 [00:47<00:44,  3.10it/s]
+
 52%|█████▏    | 150/288 [00:48<00:44,  3.13it/s]
+
 52%|█████▏    | 151/288 [00:48<00:49,  2.77it/s]
+
 53%|█████▎    | 152/288 [00:49<00:48,  2.82it/s]
+
 53%|█████▎    | 153/288 [00:49<00:45,  2.99it/s]
+
 53%|█████▎    | 154/288 [00:49<00:45,  2.93it/s]
+
 54%|█████▍    | 155/288 [00:50<00:44,  2.96it/s]
+
 54%|█████▍    | 156/288 [00:50<00:43,  3.03it/s]
+
 55%|███���█▍    | 157/288 [00:50<00:43,  3.03it/s]
+
 55%|█████▍    | 158/288 [00:51<00:50,  2.58it/s]
+
 55%|█████▌    | 159/288 [00:51<00:47,  2.69it/s]
+
 56%|█████▌    | 160/288 [00:51<00:44,  2.88it/s]
+
 56%|█████▌    | 161/288 [00:52<00:41,  3.02it/s]
+
 56%|█████▋    | 162/288 [00:52<00:40,  3.14it/s]
+
 57%|█████▋    | 163/288 [00:52<00:40,  3.09it/s]
+
 57%|█████▋    | 164/288 [00:53<00:45,  2.75it/s]
+
 57%|█████▋    | 165/288 [00:53<00:43,  2.83it/s]
+
 58%|█████▊    | 166/288 [00:53<00:42,  2.87it/s]
+
 58%|█████▊    | 167/288 [00:54<00:40,  2.99it/s]
+
 58%|█████▊    | 168/288 [00:54<00:40,  2.93it/s]
+
 59%|█████▊    | 169/288 [00:54<00:40,  2.94it/s]
+
 59%|█████▉    | 170/288 [00:55<00:45,  2.57it/s]
+
 59%|█████▉    | 171/288 [00:55<00:43,  2.68it/s]
+
 60%|█████▉    | 172/288 [00:56<00:41,  2.79it/s]
+
 60%|██████    | 173/288 [00:56<00:40,  2.83it/s]
+
 60%|██████    | 174/288 [00:56<00:39,  2.89it/s]
+
 61%|██████    | 175/288 [00:57<00:37,  3.01it/s]
+
 61%|██████    | 176/288 [00:57<00:51,  2.17it/s]
+
 61%|██████▏   | 177/288 [00:58<00:47,  2.36it/s]
+
 62%|██████▏   | 178/288 [00:58<00:43,  2.50it/s]
+
 62%|██████▏   | 179/288 [00:58<00:40,  2.67it/s]
+
 62%|██████▎   | 180/288 [00:59<00:39,  2.77it/s]
+
 63%|██████▎   | 181/288 [00:59<00:39,  2.69it/s]
+
 63%|██████▎   | 182/288 [00:59<00:39,  2.71it/s]
+
 64%|██████▎   | 183/288 [01:00<00:37,  2.82it/s]
+
 64%|██████▍   | 184/288 [01:00<00:36,  2.86it/s]
+
 64%|██████▍   | 185/288 [01:00<00:35,  2.92it/s]
+
 65%|██████▍   | 186/288 [01:01<00:38,  2.62it/s]
+
 65%|██████▍   | 187/288 [01:01<00:38,  2.63it/s]
+
 65%|██████▌   | 188/288 [01:02<00:36,  2.74it/s]
+
 66%|██████▌   | 189/288 [01:02<00:34,  2.90it/s]
+
 66%|██████▌   | 190/288 [01:02<00:34,  2.81it/s]
+
 66%|██████▋   | 191/288 [01:03<00:39,  2.43it/s]
+
 67%|██████▋   | 192/288 [01:03<00:36,  2.65it/s]
+
 67%|██████▋   | 193/288 [01:03<00:34,  2.76it/s]
+
 67%|██████▋   | 194/288 [01:04<00:34,  2.72it/s]
+
 68%|██████▊   | 195/288 [01:04<00:33,  2.80it/s]
+
 68%|██████▊   | 196/288 [01:05<00:39,  2.31it/s]
+
 68%|██████▊   | 197/288 [01:05<00:36,  2.47it/s]
+
 69%|██████▉   | 198/288 [01:05<00:33,  2.72it/s]
+
 69%|██████▉   | 199/288 [01:06<00:31,  2.82it/s]
+
 69%|██████▉   | 200/288 [01:06<00:29,  3.00it/s]
+
 70%|██████▉   | 201/288 [01:06<00:35,  2.46it/s]
+
 70%|███████   | 202/288 [01:07<00:32,  2.62it/s]
+
 70%|███████   | 203/288 [01:07<00:31,  2.73it/s]
+
 71%|███████   | 204/288 [01:07<00:29,  2.82it/s]
+
 71%|███████   | 205/288 [01:08<00:28,  2.95it/s]
+
 72%|███████▏  | 206/288 [01:08<00:33,  2.42it/s]
+
 72%|███████▏  | 207/288 [01:09<00:32,  2.50it/s]
+
 72%|███████▏  | 208/288 [01:09<00:31,  2.57it/s]
+
 73%|███████▎  | 209/288 [01:09<00:30,  2.61it/s]
+
 73%|███████▎  | 210/288 [01:10<00:27,  2.87it/s]
+
 73%|███████▎  | 211/288 [01:10<00:36,  2.14it/s]
+
 74%|███████▎  | 212/288 [01:11<00:32,  2.36it/s]
+
 74%|███████▍  | 213/288 [01:11<00:31,  2.38it/s]
+
 74%|███████▍  | 214/288 [01:12<00:29,  2.54it/s]
+
 75%|███████▍  | 215/288 [01:12<00:31,  2.30it/s]
+
 75%|███████▌  | 216/288 [01:12<00:29,  2.45it/s]
+
 75%|███████▌  | 217/288 [01:13<00:26,  2.67it/s]
+
 76%|███████▌  | 218/288 [01:13<00:25,  2.72it/s]
+
 76%|███████▌  | 219/288 [01:14<00:29,  2.32it/s]
+
 76%|███████▋  | 220/288 [01:14<00:28,  2.37it/s]
+
 77%|███████▋  | 221/288 [01:14<00:26,  2.49it/s]
+
 77%|███████▋  | 222/288 [01:15<00:26,  2.54it/s]
+
 77%|███████▋  | 223/288 [01:15<00:28,  2.30it/s]
+
 78%|███████▊  | 224/288 [01:16<00:26,  2.45it/s]
+
 78%|███████▊  | 225/288 [01:16<00:24,  2.61it/s]
+
 78%|███████▊  | 226/288 [01:16<00:22,  2.72it/s]
+
 79%|███████▉  | 227/288 [01:17<00:27,  2.25it/s]
+
 79%|███████▉  | 228/288 [01:17<00:24,  2.40it/s]
+
 80%|███████▉  | 229/288 [01:18<00:23,  2.54it/s]
+
 80%|███████▉  | 230/288 [01:18<00:21,  2.66it/s]
+
 80%|████��███  | 231/288 [01:19<00:25,  2.23it/s]
+
 81%|████████  | 232/288 [01:19<00:22,  2.44it/s]
+
 81%|████████  | 233/288 [01:19<00:21,  2.53it/s]
+
 81%|████████▏ | 234/288 [01:20<00:19,  2.71it/s]
+
 82%|████████▏ | 235/288 [01:20<00:25,  2.12it/s]
+
 82%|████████▏ | 236/288 [01:21<00:22,  2.28it/s]
+
 82%|████████▏ | 237/288 [01:21<00:21,  2.41it/s]
+
 83%|████████▎ | 238/288 [01:21<00:20,  2.50it/s]
+
 83%|████████▎ | 239/288 [01:22<00:24,  2.00it/s]
+
 83%|████████▎ | 240/288 [01:22<00:21,  2.27it/s]
+
 84%|████████▎ | 241/288 [01:23<00:19,  2.42it/s]
+
 84%|████████▍ | 242/288 [01:23<00:18,  2.54it/s]
+
 84%|████████▍ | 243/288 [01:24<00:21,  2.06it/s]
+
 85%|████████▍ | 244/288 [01:24<00:19,  2.24it/s]
+
 85%|████████▌ | 245/288 [01:25<00:17,  2.39it/s]
+
 85%|████████▌ | 246/288 [01:25<00:17,  2.45it/s]
+
 86%|████████▌ | 247/288 [01:26<00:20,  2.02it/s]
+
 86%|████████▌ | 248/288 [01:26<00:17,  2.25it/s]
+
 86%|████████▋ | 249/288 [01:26<00:16,  2.37it/s]
+
 87%|████████▋ | 250/288 [01:27<00:15,  2.45it/s]
+
 87%|████████▋ | 251/288 [01:27<00:19,  1.93it/s]
+
 88%|████████▊ | 252/288 [01:28<00:17,  2.10it/s]
+
 88%|████████▊ | 253/288 [01:28<00:14,  2.34it/s]
+
 88%|████████▊ | 254/288 [01:29<00:15,  2.19it/s]
+
 89%|████████▊ | 255/288 [01:29<00:13,  2.44it/s]
+
 89%|████████▉ | 256/288 [01:29<00:12,  2.56it/s]
+
 89%|████████▉ | 257/288 [01:30<00:14,  2.19it/s]
+
 90%|████████▉ | 258/288 [01:30<00:13,  2.30it/s]
+
 90%|████████▉ | 259/288 [01:31<00:12,  2.39it/s]
+
 90%|█████████ | 260/288 [01:31<00:13,  2.08it/s]
+
 91%|█████████ | 261/288 [01:32<00:11,  2.26it/s]
+
 91%|█████████ | 262/288 [01:32<00:10,  2.41it/s]
+
 91%|█████████▏| 263/288 [01:33<00:11,  2.10it/s]
+
 92%|█████████▏| 264/288 [01:33<00:10,  2.26it/s]
+
 92%|█████████▏| 265/288 [01:33<00:09,  2.39it/s]
+
 92%|█████████▏| 266/288 [01:34<00:10,  2.08it/s]
+
 93%|█████████▎| 267/288 [01:34<00:09,  2.20it/s]
+
 93%|█████████▎| 268/288 [01:35<00:08,  2.38it/s]
+
 93%|█████████▎| 269/288 [01:35<00:09,  2.00it/s]
+
 94%|█████████▍| 270/288 [01:36<00:08,  2.11it/s]
+
 94%|█████████▍| 271/288 [01:36<00:07,  2.28it/s]
+
 94%|█████████▍| 272/288 [01:37<00:08,  1.85it/s]
+
 95%|█████████▍| 273/288 [01:37<00:07,  2.08it/s]
+
 95%|█████████▌| 274/288 [01:38<00:06,  2.28it/s]
+
 95%|█████████▌| 275/288 [01:38<00:06,  1.89it/s]
+
 96%|█████████▌| 276/288 [01:39<00:05,  2.12it/s]
+
 96%|█████████▌| 277/288 [01:39<00:04,  2.29it/s]
+
 97%|█████████▋| 278/288 [01:40<00:05,  1.78it/s]
+
 97%|█████████▋| 279/288 [01:40<00:04,  2.05it/s]
+
 97%|█████████▋| 280/288 [01:41<00:03,  2.24it/s]
+
 98%|█████████▊| 281/288 [01:41<00:03,  1.83it/s]
+
 98%|█████████▊| 282/288 [01:42<00:02,  2.06it/s]
+
 98%|█████████▊| 283/288 [01:42<00:02,  2.17it/s]
+
 99%|█████████▊| 284/288 [01:43<00:02,  1.80it/s]
+
 99%|█████████▉| 285/288 [01:43<00:01,  2.05it/s]
+
 99%|█████████▉| 286/288 [01:44<00:00,  2.26it/s]
+
+
                                                      
+
                                                 
  1%|▏         | 500/37300 [15:13<14:56:05,  1.46s/it]
+
+
                                                 Saving model checkpoint to ./checkpoint-500
+Configuration saved in ./checkpoint-500/config.json
+Model weights saved in ./checkpoint-500/pytorch_model.bin
+Configuration saved in ./checkpoint-500/preprocessor_config.json
+Configuration saved in ./preprocessor_config.json

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:572879a364a49fa364fbb6c4c85b5ca6ca71adfa5d735fdd625948ca4a5d6f55
+size 1276909233

run.sh

@@ -0,0 +1,37 @@
+python run_speech_recognition_ctc.py \
+	--dataset_name="common_voice" \
+	--model_name_or_path="facebook/wav2vec2-xls-r-300m" \
+	--dataset_config_name="zh-HK" \
+	--output_dir="./" \
+	--overwrite_output_dir \
+	--num_train_epochs="100" \
+	--per_device_train_batch_size="8" \
+	--per_device_eval_batch_size="8" \
+	--gradient_accumulation_steps="4" \
+	--learning_rate="1e-4" \
+	--warmup_steps="2000" \
+	--length_column_name="input_length" \
+    --max_duration_in_seconds="7" \
+    --max_eval_samples="3000" \
+	--evaluation_strategy="steps" \
+	--text_column_name="sentence" \
+	--chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – ！ － ： – 。 》 , ） , ？ ； ～ ~ … ︰ ， （ 」 ‧ 《 ﹔ 、 — ／ , 「 ﹖ · \
+	--save_steps="500" \
+	--eval_steps="500" \
+	--logging_steps="100" \
+	--layerdrop="0.0" \
+	--activation_dropout="0.1" \
+	--save_total_limit="3" \
+	--freeze_feature_encoder \
+	--feat_proj_dropout="0.0" \
+	--mask_time_prob="0.75" \
+	--mask_time_length="10" \
+	--mask_feature_prob="0.25" \
+	--mask_feature_length="64" \
+	--gradient_checkpointing \
+	--use_auth_token \
+	--fp16 \
+	--group_by_length \
+	--do_train --do_eval \
+    --report_to="tensorboard" \
+	--push_to_hub

run_speech_recognition_ctc.py

@@ -0,0 +1,829 @@
+#!/usr/bin/env python
+# coding=utf-8
+# Copyright 2021 The HuggingFace Inc. team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+
+""" Fine-tuning a 🤗 Transformers CTC model for automatic speech recognition"""
+
+import functools
+import json
+import logging
+import os
+import re
+import sys
+import warnings
+from dataclasses import dataclass, field
+from typing import Dict, List, Optional, Union
+
+import datasets
+import numpy as np
+import torch
+from datasets import DatasetDict, load_dataset, load_metric
+
+import transformers
+from transformers import (
+    AutoConfig,
+    AutoFeatureExtractor,
+    AutoModelForCTC,
+    AutoProcessor,
+    AutoTokenizer,
+    HfArgumentParser,
+    Trainer,
+    TrainingArguments,
+    Wav2Vec2Processor,
+    set_seed,
+)
+from transformers.trainer_utils import get_last_checkpoint, is_main_process
+from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
+
+
+# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
+check_min_version("4.17.0.dev0")
+
+require_version(
+    "datasets>=1.13.3",
+    "To fix: pip install -r examples/pytorch/text-classification/requirements.txt",
+)
+
+
+logger = logging.getLogger(__name__)
+
+
+def list_field(default=None, metadata=None):
+    return field(default_factory=lambda: default, metadata=metadata)
+
+
+@dataclass
+class ModelArguments:
+    """
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
+    """
+
+    model_name_or_path: str = field(
+        metadata={
+            "help": "Path to pretrained model or model identifier from huggingface.co/models"
+        }
+    )
+    tokenizer_name_or_path: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "Path to pretrained tokenizer or tokenizer identifier from huggingface.co/models"
+        },
+    )
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "Where do you want to store the pretrained models downloaded from huggingface.co"
+        },
+    )
+    freeze_feature_encoder: bool = field(
+        default=True,
+        metadata={"help": "Whether to freeze the feature encoder layers of the model."},
+    )
+    attention_dropout: float = field(
+        default=0.0,
+        metadata={"help": "The dropout ratio for the attention probabilities."},
+    )
+    activation_dropout: float = field(
+        default=0.0,
+        metadata={
+            "help": "The dropout ratio for activations inside the fully connected layer."
+        },
+    )
+    feat_proj_dropout: float = field(
+        default=0.0, metadata={"help": "The dropout ratio for the projected features."}
+    )
+    hidden_dropout: float = field(
+        default=0.0,
+        metadata={
+            "help": "The dropout probability for all fully connected layers in the embeddings, encoder, and pooler."
+        },
+    )
+    final_dropout: float = field(
+        default=0.0,
+        metadata={"help": "The dropout probability for the final projection layer."},
+    )
+    mask_time_prob: float = field(
+        default=0.05,
+        metadata={
+            "help": "Probability of each feature vector along the time axis to be chosen as the start of the vector"
+            "span to be masked. Approximately ``mask_time_prob * sequence_length // mask_time_length`` feature"
+            "vectors will be masked along the time axis."
+        },
+    )
+    mask_time_length: int = field(
+        default=10,
+        metadata={"help": "Length of vector span to mask along the time axis."},
+    )
+    mask_feature_prob: float = field(
+        default=0.0,
+        metadata={
+            "help": "Probability of each feature vector along the feature axis to be chosen as the start of the vector"
+            "span to be masked. Approximately ``mask_feature_prob * sequence_length // mask_feature_length`` feature bins will be masked along the time axis."
+        },
+    )
+    mask_feature_length: int = field(
+        default=10,
+        metadata={"help": "Length of vector span to mask along the feature axis."},
+    )
+    layerdrop: float = field(
+        default=0.0, metadata={"help": "The LayerDrop probability."}
+    )
+    ctc_loss_reduction: Optional[str] = field(
+        default="mean",
+        metadata={
+            "help": "The way the ctc loss should be reduced. Should be one of 'mean' or 'sum'."
+        },
+    )
+
+
+@dataclass
+class DataTrainingArguments:
+    """
+    Arguments pertaining to what data we are going to input our model for training and eval.
+
+    Using `HfArgumentParser` we can turn this class
+    into argparse arguments to be able to specify them on
+    the command line.
+    """
+
+    dataset_name: str = field(
+        metadata={
+            "help": "The configuration name of the dataset to use (via the datasets library)."
+        }
+    )
+    dataset_config_name: str = field(
+        default=None,
+        metadata={
+            "help": "The configuration name of the dataset to use (via the datasets library)."
+        },
+    )
+    train_split_name: str = field(
+        default="train+validation",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
+        },
+    )
+    eval_split_name: str = field(
+        default="test",
+        metadata={
+            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'test'"
+        },
+    )
+    audio_column_name: str = field(
+        default="audio",
+        metadata={
+            "help": "The name of the dataset column containing the audio data. Defaults to 'audio'"
+        },
+    )
+    text_column_name: str = field(
+        default="text",
+        metadata={
+            "help": "The name of the dataset column containing the text data. Defaults to 'text'"
+        },
+    )
+    overwrite_cache: bool = field(
+        default=False,
+        metadata={"help": "Overwrite the cached preprocessed datasets or not."},
+    )
+    preprocessing_num_workers: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of processes to use for the preprocessing."},
+    )
+    max_train_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": "For debugging purposes or quicker training, truncate the number of training examples to this "
+            "value if set."
+        },
+    )
+    max_eval_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
+            "value if set."
+        },
+    )
+    chars_to_ignore: Optional[List[str]] = list_field(
+        default=None,
+        metadata={"help": "A list of characters to remove from the transcripts."},
+    )
+    eval_metrics: List[str] = list_field(
+        default=["wer", "cer"],
+        metadata={
+            "help": "A list of metrics the model should be evaluated on. E.g. `'wer cer'`"
+        },
+    )
+    max_duration_in_seconds: float = field(
+        default=20.0,
+        metadata={
+            "help": "Filter audio files that are longer than `max_duration_in_seconds` seconds to 'max_duration_in_seconds`"
+        },
+    )
+    min_duration_in_seconds: float = field(
+        default=0.0,
+        metadata={
+            "help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"
+        },
+    )
+    preprocessing_only: bool = field(
+        default=False,
+        metadata={
+            "help": "Whether to only do data preprocessing and skip training. "
+            "This is especially useful when data preprocessing errors out in distributed training due to timeout. "
+            "In this case, one should run the preprocessing in a non-distributed setup with `preprocessing_only=True` "
+            "so that the cached datasets can consequently be loaded in distributed training"
+        },
+    )
+    use_auth_token: bool = field(
+        default=False,
+        metadata={
+            "help": "If :obj:`True`, will use the token generated when running"
+            ":obj:`transformers-cli login` as HTTP bearer authorization for remote files."
+        },
+    )
+    unk_token: str = field(
+        default="[UNK]", metadata={"help": "The unk token for the tokenizer"},
+    )
+    pad_token: str = field(
+        default="[PAD]", metadata={"help": "The padding token for the tokenizer"},
+    )
+    word_delimiter_token: str = field(
+        default="|", metadata={"help": "The word delimiter token for the tokenizer"},
+    )
+    phoneme_language: Optional[str] = field(
+        default=None,
+        metadata={
+            "help": "The target language that should be used be"
+            " passed to the tokenizer for tokenization. Note that"
+            " this is only relevant if the model classifies the"
+            " input audio to a sequence of phoneme sequences."
+        },
+    )
+
+
+@dataclass
+class DataCollatorCTCWithPadding:
+    """
+    Data collator that will dynamically pad the inputs received.
+    Args:
+        processor (:class:`~transformers.AutoProcessor`)
+            The processor used for proccessing the data.
+        padding (:obj:`bool`, :obj:`str` or :class:`~transformers.tokenization_utils_base.PaddingStrategy`, `optional`, defaults to :obj:`True`):
+            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)
+            among:
+            * :obj:`True` or :obj:`'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
+              sequence if provided).
+            * :obj:`'max_length'`: Pad to a maximum length specified with the argument :obj:`max_length` or to the
+              maximum acceptable input length for the model if that argument is not provided.
+            * :obj:`False` or :obj:`'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of
+              different lengths).
+        max_length (:obj:`int`, `optional`):
+            Maximum length of the ``input_values`` of the returned list and optionally padding length (see above).
+        max_length_labels (:obj:`int`, `optional`):
+            Maximum length of the ``labels`` returned list and optionally padding length (see above).
+        pad_to_multiple_of (:obj:`int`, `optional`):
+            If set will pad the sequence to a multiple of the provided value.
+            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=
+            7.5 (Volta).
+    """
+
+    processor: AutoProcessor
+    padding: Union[bool, str] = "longest"
+    pad_to_multiple_of: Optional[int] = None
+    pad_to_multiple_of_labels: Optional[int] = None
+
+    def __call__(
+        self, features: List[Dict[str, Union[List[int], torch.Tensor]]]
+    ) -> Dict[str, torch.Tensor]:
+        # split inputs and labels since they have to be of different lenghts and need
+        # different padding methods
+        input_features = [
+            {"input_values": feature["input_values"]} for feature in features
+        ]
+        label_features = [{"input_ids": feature["labels"]} for feature in features]
+
+        batch = self.processor.pad(
+            input_features,
+            padding=self.padding,
+            pad_to_multiple_of=self.pad_to_multiple_of,
+            return_tensors="pt",
+        )
+
+        with self.processor.as_target_processor():
+            labels_batch = self.processor.pad(
+                label_features,
+                padding=self.padding,
+                pad_to_multiple_of=self.pad_to_multiple_of_labels,
+                return_tensors="pt",
+            )
+
+        # replace padding with -100 to ignore loss correctly
+        labels = labels_batch["input_ids"].masked_fill(
+            labels_batch.attention_mask.ne(1), -100
+        )
+
+        batch["labels"] = labels
+
+        return batch
+
+
+def create_vocabulary_from_data(
+    datasets: DatasetDict,
+    word_delimiter_token: Optional[str] = None,
+    unk_token: Optional[str] = None,
+    pad_token: Optional[str] = None,
+):
+    # Given training and test labels create vocabulary
+    def extract_all_chars(batch):
+        all_text = " ".join(batch["target_text"])
+        vocab = list(set(all_text))
+        return {"vocab": [vocab], "all_text": [all_text]}
+
+    vocabs = datasets.map(
+        extract_all_chars,
+        batched=True,
+        batch_size=-1,
+        keep_in_memory=True,
+        remove_columns=datasets["train"].column_names,
+    )
+
+    # take union of all unique characters in each dataset
+    vocab_set = functools.reduce(
+        lambda vocab_1, vocab_2: set(vocab_1["vocab"][0]) | set(vocab_2["vocab"][0]),
+        vocabs.values(),
+    )
+
+    vocab_dict = {v: k for k, v in enumerate(sorted(list(vocab_set)))}
+
+    # replace white space with delimiter token
+    if word_delimiter_token is not None:
+        vocab_dict[word_delimiter_token] = vocab_dict[" "]
+        del vocab_dict[" "]
+
+    # add unk and pad token
+    if unk_token is not None:
+        vocab_dict[unk_token] = len(vocab_dict)
+
+    if pad_token is not None:
+        vocab_dict[pad_token] = len(vocab_dict)
+
+    return vocab_dict
+
+
+def main():
+    # See all possible arguments in src/transformers/training_args.py
+    # or by passing the --help flag to this script.
+    # We now keep distinct sets of args, for a cleaner separation of concerns.
+
+    parser = HfArgumentParser(
+        (ModelArguments, DataTrainingArguments, TrainingArguments)
+    )
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args, data_args, training_args = parser.parse_json_file(
+            json_file=os.path.abspath(sys.argv[1])
+        )
+    else:
+        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
+
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if (
+        os.path.isdir(training_args.output_dir)
+        and training_args.do_train
+        and not training_args.overwrite_output_dir
+    ):
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+
+    # Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+    logger.setLevel(
+        logging.INFO if is_main_process(training_args.local_rank) else logging.WARN
+    )
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    # Set the verbosity to info of the Transformers logger (on main process only):
+    if is_main_process(training_args.local_rank):
+        transformers.utils.logging.set_verbosity_info()
+    logger.info("Training/evaluation parameters %s", training_args)
+
+    # Set seed before initializing model.
+    set_seed(training_args.seed)
+
+    # 1. First, let's load the dataset
+    raw_datasets = DatasetDict()
+
+    if training_args.do_train:
+        raw_datasets["train"] = load_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.train_split_name,
+            use_auth_token=data_args.use_auth_token,
+        )
+
+        if data_args.audio_column_name not in raw_datasets["train"].column_names:
+            raise ValueError(
+                f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
+                "Make sure to set `--audio_column_name` to the correct audio column - one of "
+                f"{', '.join(raw_datasets['train'].column_names)}."
+            )
+
+        if data_args.text_column_name not in raw_datasets["train"].column_names:
+            raise ValueError(
+                f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
+                "Make sure to set `--text_column_name` to the correct text column - one of "
+                f"{', '.join(raw_datasets['train'].column_names)}."
+            )
+
+        if data_args.max_train_samples is not None:
+            raw_datasets["train"] = raw_datasets["train"].select(
+                range(data_args.max_train_samples)
+            )
+
+    if training_args.do_eval:
+        raw_datasets["eval"] = load_dataset(
+            data_args.dataset_name,
+            data_args.dataset_config_name,
+            split=data_args.eval_split_name,
+            use_auth_token=data_args.use_auth_token,
+        )
+
+        if data_args.max_eval_samples is not None:
+            raw_datasets["eval"] = raw_datasets["eval"].select(
+                range(data_args.max_eval_samples)
+            )
+
+    # 2. We remove some special characters from the datasets
+    # that make training complicated and do not help in transcribing the speech
+    # E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
+    # that could be easily picked up by the model
+    chars_to_ignore_regex = (
+        f'[{"".join(data_args.chars_to_ignore)}]'
+        if data_args.chars_to_ignore is not None
+        else None
+    )
+    text_column_name = data_args.text_column_name
+
+    def remove_special_characters(batch):
+        if chars_to_ignore_regex is not None:
+            batch["target_text"] = (
+                re.sub(chars_to_ignore_regex, "", batch[text_column_name]).lower() + " "
+            )
+        else:
+            batch["target_text"] = batch[text_column_name].lower() + " "
+        return batch
+
+    with training_args.main_process_first(
+        desc="dataset map special characters removal"
+    ):
+        raw_datasets = raw_datasets.map(
+            remove_special_characters,
+            remove_columns=[text_column_name],
+            desc="remove special characters from datasets",
+        )
+
+    # save special tokens for tokenizer
+    word_delimiter_token = data_args.word_delimiter_token
+    unk_token = data_args.unk_token
+    pad_token = data_args.pad_token
+
+    # 3. Next, let's load the config as we might need it to create
+    # the tokenizer
+    # load config
+    config = AutoConfig.from_pretrained(
+        model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        use_auth_token=data_args.use_auth_token,
+    )
+
+    # 4. Next, if no tokenizer file is defined,
+    # we create the vocabulary of the model by extracting all unique characters from
+    # the training and evaluation datasets
+    # We need to make sure that only first rank saves vocabulary
+    # make sure all processes wait until vocab is created
+    tokenizer_name_or_path = model_args.tokenizer_name_or_path
+    tokenizer_kwargs = {}
+    if tokenizer_name_or_path is None:
+        # save vocab in training output dir
+        tokenizer_name_or_path = training_args.output_dir
+
+        vocab_file = os.path.join(tokenizer_name_or_path, "vocab.json")
+
+        with training_args.main_process_first():
+            if training_args.overwrite_output_dir and os.path.isfile(vocab_file):
+                os.remove(vocab_file)
+
+        with training_args.main_process_first(desc="dataset map vocabulary creation"):
+            if not os.path.isfile(vocab_file):
+                os.makedirs(tokenizer_name_or_path, exist_ok=True)
+                vocab_dict = create_vocabulary_from_data(
+                    raw_datasets,
+                    word_delimiter_token=word_delimiter_token,
+                    unk_token=unk_token,
+                    pad_token=pad_token,
+                )
+
+                # save vocab dict to be loaded into tokenizer
+                with open(vocab_file, "w") as file:
+                    json.dump(vocab_dict, file)
+
+        # if tokenizer has just been created
+        # it is defined by `tokenizer_class` if present in config else by `model_type`
+        tokenizer_kwargs = {
+            "config": config if config.tokenizer_class is not None else None,
+            "tokenizer_type": config.model_type
+            if config.tokenizer_class is None
+            else None,
+            "unk_token": unk_token,
+            "pad_token": pad_token,
+            "word_delimiter_token": word_delimiter_token,
+        }
+
+    # 5. Now we can instantiate the feature extractor, tokenizer and model
+    # Note for distributed training, the .from_pretrained methods guarantee that only
+    # one local process can concurrently download model & vocab.
+
+    # load feature_extractor and tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(
+        tokenizer_name_or_path,
+        use_auth_token=data_args.use_auth_token,
+        **tokenizer_kwargs,
+    )
+    feature_extractor = AutoFeatureExtractor.from_pretrained(
+        model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        use_auth_token=data_args.use_auth_token,
+    )
+
+    # adapt config
+    config.update(
+        {
+            "feat_proj_dropout": model_args.feat_proj_dropout,
+            "attention_dropout": model_args.attention_dropout,
+            "hidden_dropout": model_args.hidden_dropout,
+            "final_dropout": model_args.final_dropout,
+            "mask_time_prob": model_args.mask_time_prob,
+            "mask_time_length": model_args.mask_time_length,
+            "mask_feature_prob": model_args.mask_feature_prob,
+            "mask_feature_length": model_args.mask_feature_length,
+            "gradient_checkpointing": training_args.gradient_checkpointing,
+            "layerdrop": model_args.layerdrop,
+            "ctc_loss_reduction": model_args.ctc_loss_reduction,
+            "pad_token_id": tokenizer.pad_token_id,
+            "vocab_size": len(tokenizer),
+            "activation_dropout": model_args.activation_dropout,
+        }
+    )
+
+    # create model
+    model = AutoModelForCTC.from_pretrained(
+        model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        config=config,
+        use_auth_token=data_args.use_auth_token,
+    )
+
+    # freeze encoder
+    if model_args.freeze_feature_encoder:
+        model.freeze_feature_encoder()
+
+    # 6. Now we preprocess the datasets including loading the audio, resampling and normalization
+    # Thankfully, `datasets` takes care of automatically loading and resampling the audio,
+    # so that we just need to set the correct target sampling rate and normalize the input
+    # via the `feature_extractor`
+
+    # make sure that dataset decodes audio with correct sampling rate
+    dataset_sampling_rate = (
+        next(iter(raw_datasets.values()))
+        .features[data_args.audio_column_name]
+        .sampling_rate
+    )
+    if dataset_sampling_rate != feature_extractor.sampling_rate:
+        raw_datasets = raw_datasets.cast_column(
+            data_args.audio_column_name,
+            datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate),
+        )
+
+    # derive max & min input length for sample rate & max duration
+    max_input_length = (
+        data_args.max_duration_in_seconds * feature_extractor.sampling_rate
+    )
+    min_input_length = (
+        data_args.min_duration_in_seconds * feature_extractor.sampling_rate
+    )
+    audio_column_name = data_args.audio_column_name
+    num_workers = data_args.preprocessing_num_workers
+
+    # `phoneme_language` is only relevant if the model is fine-tuned on phoneme classification
+    phoneme_language = data_args.phoneme_language
+
+    # Preprocessing the datasets.
+    # We need to read the audio files as arrays and tokenize the targets.
+    def prepare_dataset(batch):
+        # load audio
+        sample = batch[audio_column_name]
+
+        inputs = feature_extractor(
+            sample["array"], sampling_rate=sample["sampling_rate"]
+        )
+        batch["input_values"] = inputs.input_values[0]
+        batch["input_length"] = len(batch["input_values"])
+
+        # encode targets
+        additional_kwargs = {}
+        if phoneme_language is not None:
+            additional_kwargs["phonemizer_lang"] = phoneme_language
+
+        batch["labels"] = tokenizer(batch["target_text"], **additional_kwargs).input_ids
+        return batch
+
+    with training_args.main_process_first(desc="dataset map preprocessing"):
+        vectorized_datasets = raw_datasets.map(
+            prepare_dataset,
+            remove_columns=next(iter(raw_datasets.values())).column_names,
+            num_proc=num_workers,
+            desc="preprocess datasets",
+        )
+
+        def is_audio_in_length_range(length):
+            return length > min_input_length and length < max_input_length
+
+        # filter data that is shorter than min_input_length
+        vectorized_datasets = vectorized_datasets.filter(
+            is_audio_in_length_range,
+            num_proc=num_workers,
+            input_columns=["input_length"],
+        )
+
+    # 7. Next, we can prepare the training.
+    # Let's use word error rate (WER) as our evaluation metric,
+    # instantiate a data collator and the trainer
+
+    # Define evaluation metrics during training, *i.e.* word error rate, character error rate
+    eval_metrics = {metric: load_metric(metric) for metric in data_args.eval_metrics}
+
+    # for large datasets it is advised to run the preprocessing on a
+    # single machine first with ``args.preprocessing_only`` since there will mostly likely
+    # be a timeout when running the script in distributed mode.
+    # In a second step ``args.preprocessing_only`` can then be set to `False` to load the
+    # cached dataset
+    if data_args.preprocessing_only:
+        logger.info(
+            f"Data preprocessing finished. Files cached at {vectorized_datasets.cache_files}"
+        )
+        return
+
+    def compute_metrics(pred):
+        pred_logits = pred.predictions
+        pred_ids = np.argmax(pred_logits, axis=-1)
+
+        pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
+
+        pred_str = tokenizer.batch_decode(pred_ids)
+        # we do not want to group tokens when computing the metrics
+        label_str = tokenizer.batch_decode(pred.label_ids, group_tokens=False)
+
+        metrics = {
+            k: v.compute(predictions=pred_str, references=label_str)
+            for k, v in eval_metrics.items()
+        }
+
+        return metrics
+
+    # Now save everything to be able to create a single processor later
+    if is_main_process(training_args.local_rank):
+        # save feature extractor, tokenizer and config
+        feature_extractor.save_pretrained(training_args.output_dir)
+        tokenizer.save_pretrained(training_args.output_dir)
+        config.save_pretrained(training_args.output_dir)
+
+    try:
+        processor = AutoProcessor.from_pretrained(training_args.output_dir)
+    except (OSError, KeyError):
+        warnings.warn(
+            "Loading a processor from a feature extractor config that does not"
+            " include a `processor_class` attribute is deprecated and will be removed in v5. Please add the following "
+            " attribute to your `preprocessor_config.json` file to suppress this warning: "
+            " `'processor_class': 'Wav2Vec2Processor'`",
+            FutureWarning,
+        )
+        processor = Wav2Vec2Processor.from_pretrained(training_args.output_dir)
+
+    # Instantiate custom data collator
+    data_collator = DataCollatorCTCWithPadding(processor=processor)
+
+    # Initialize Trainer
+    trainer = Trainer(
+        model=model,
+        data_collator=data_collator,
+        args=training_args,
+        compute_metrics=compute_metrics,
+        train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
+        eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
+        tokenizer=feature_extractor,
+    )
+
+    # 8. Finally, we can start training
+
+    # Training
+    if training_args.do_train:
+
+        # use last checkpoint if exist
+        if last_checkpoint is not None:
+            checkpoint = last_checkpoint
+        elif os.path.isdir(model_args.model_name_or_path):
+            checkpoint = model_args.model_name_or_path
+        else:
+            checkpoint = None
+
+        train_result = trainer.train(resume_from_checkpoint=checkpoint)
+        trainer.save_model()
+
+        metrics = train_result.metrics
+        max_train_samples = (
+            data_args.max_train_samples
+            if data_args.max_train_samples is not None
+            else len(vectorized_datasets["train"])
+        )
+        metrics["train_samples"] = min(
+            max_train_samples, len(vectorized_datasets["train"])
+        )
+
+        trainer.log_metrics("train", metrics)
+        trainer.save_metrics("train", metrics)
+        trainer.save_state()
+
+    # Evaluation
+    results = {}
+    if training_args.do_eval:
+        logger.info("*** Evaluate ***")
+        metrics = trainer.evaluate()
+        max_eval_samples = (
+            data_args.max_eval_samples
+            if data_args.max_eval_samples is not None
+            else len(vectorized_datasets["eval"])
+        )
+        metrics["eval_samples"] = min(
+            max_eval_samples, len(vectorized_datasets["eval"])
+        )
+
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # Write model card and (optionally) push to hub
+    config_name = (
+        data_args.dataset_config_name
+        if data_args.dataset_config_name is not None
+        else "na"
+    )
+    kwargs = {
+        "finetuned_from": model_args.model_name_or_path,
+        "tasks": "speech-recognition",
+        "tags": ["automatic-speech-recognition", data_args.dataset_name],
+        "dataset_args": f"Config: {config_name}, Training split: {data_args.train_split_name}, Eval split: {data_args.eval_split_name}",
+        "dataset": f"{data_args.dataset_name.upper()} - {config_name.upper()}",
+    }
+    if "common_voice" in data_args.dataset_name:
+        kwargs["language"] = config_name
+
+    if training_args.push_to_hub:
+        trainer.push_to_hub(**kwargs)
+    else:
+        trainer.create_model_card(**kwargs)
+
+    return results
+
+
+if __name__ == "__main__":
+    main()

runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/1644165171.7227242/events.out.tfevents.1644165171.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98151adf5ee89a0d86283e74254aa6f1e4356e6d7ca722e0529d9870e9c55e6
+size 4564

runs/Feb06_16-31-57_job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c/events.out.tfevents.1644165171.job-cb7cc850-8327-4ab0-bdf4-0ebe63e2788c

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d4a1bc2c2de2a345205696c1d43038bf6abda4645555b39a2341e729306471
+size 5468

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472e2ebcb99d59b6b693f009ff1df20cb7c55629d4fab148f61d3dc117b7c960
+size 2991

vocab.json

@@ -0,0 +1 @@
+{"a": 1, "b": 2, "c": 3, "d": 4, "f": 5, "g": 6, "h": 7, "i": 8, "j": 9, "l": 10, "m": 11, "n": 12, "p": 13, "q": 14, "r": 15, "s": 16, "t": 17, "u": 18, "v": 19, "w": 20, "x": 21, "y": 22, "~": 23, "⋯": 24, "⠀": 25, "⻣": 26, "ㄧ": 27, "㗎": 28, "㩒": 29, "㩿": 30, "㪐": 31, "䒏": 32, "䒐": 33, "䰧": 34, "一": 35, "丁": 36, "七": 37, "丈": 38, "三": 39, "上": 40, "下": 41, "不": 42, "丑": 43, "且": 44, "丕": 45, "世": 46, "丘": 47, "丙": 48, "丟": 49, "両": 50, "並": 51, "丫": 52, "中": 53, "丰": 54, "串": 55, "丶": 56, "丸": 57, "丹": 58, "主": 59, "丼": 60, "乃": 61, "久": 62, "义": 63, "之": 64, "乍": 65, "乎": 66, "乏": 67, "乒": 68, "乓": 69, "乖": 70, "乘": 71, "乙": 72, "乜": 73, "九": 74, "乞": 75, "也": 76, "乳": 77, "乸": 78, "乾": 79, "亂": 80, "了": 81, "予": 82, "事": 83, "二": 84, "于": 85, "互": 86, "五": 87, "井": 88, "些": 89, "亞": 90, "亡": 91, "亢": 92, "交": 93, "亦": 94, "亨": 95, "享": 96, "京": 97, "亭": 98, "亮": 99, "人": 100, "什": 101, "仁": 102, "仆": 103, "仇": 104, "今": 105, "介": 106, "仍": 107, "仔": 108, "仕": 109, "他": 110, "仗": 111, "付": 112, "仙": 113, "仞": 114, "代": 115, "令": 116, "以": 117, "仰": 118, "仲": 119, "件": 120, "任": 121, "份": 122, "仿": 123, "企": 124, "伊": 125, "伏": 126, "伐": 127, "休": 128, "伙": 129, "伯": 130, "估": 131, "伴": 132, "伶": 133, "伸": 134, "似": 135, "伽": 136, "佃": 137, "但": 138, "佈": 139, "位": 140, "低": 141, "住": 142, "佐": 143, "佑": 144, "佔": 145, "何": 146, "佗": 147, "余": 148, "佚": 149, "佛": 150, "作": 151, "你": 152, "佢": 153, "佣": 154, "佩": 155, "佬": 156, "佳": 157, "併": 158, "佻": 159, "使": 160, "侄": 161, "來": 162, "例": 163, "侍": 164, "供": 165, "依": 166, "侮": 167, "侯": 168, "侵": 169, "侶": 170, "便": 171, "係": 172, "促": 173, "俄": 174, "俊": 175, "俎": 176, "俏": 177, "俐": 178, "俗": 179, "俚": 180, "保": 181, "俠": 182, "信": 183, "俬": 184, "修": 185, "俸": 186, "俾": 187, "倉": 188, "個": 189, "倍": 190, "們": 191, "倒": 192, "候": 193, "倚": 194, "借": 195, "倦": 196, "倫": 197, "值": 198, "假": 199, "偈": 200, "偉": 201, "偏": 202, "偕": 203, "做": 204, "停": 205, "健": 206, "側": 207, "偶": 208, "偷": 209, "偽": 210, "傅": 211, "傍": 212, "傑": 213, "傘": 214, "備": 215, "傢": 216, "催": 217, "傭": 218, "傲": 219, "傳": 220, "債": 221, "傷": 222, "傻": 223, "傾": 224, "僅": 225, "像": 226, "僑": 227, "僕": 228, "僭": 229, "僱": 230, "價": 231, "僻": 232, "儀": 233, "億": 234, "儈": 235, "儍": 236, "儒": 237, "儘": 238, "優": 239, "儲": 240, "允": 241, "元": 242, "兄": 243, "充": 244, "兆": 245, "兇": 246, "先": 247, "光": 248, "克": 249, "兌": 250, "免": 251, "兒": 252, "兔": 253, "兜": 254, "入": 255, "內": 256, "全": 257, "兩": 258, "八": 259, "公": 260, "六": 261, "兮": 262, "共": 263, "兵": 264, "其": 265, "具": 266, "典": 267, "兼": 268, "内": 269, "冇": 270, "冊": 271, "再": 272, "冒": 273, "冕": 274, "冗": 275, "冚": 276, "冠": 277, "冤": 278, "冧": 279, "冬": 280, "冰": 281, "冷": 282, "准": 283, "凈": 284, "凌": 285, "凍": 286, "凝": 287, "凡": 288, "凰": 289, "凱": 290, "凳": 291, "凶": 292, "凹": 293, "出": 294, "函": 295, "刀": 296, "刁": 297, "刃": 298, "分": 299, "切": 300, "刑": 301, "划": 302, "列": 303, "初": 304, "判": 305, "別": 306, "刨": 307, "利": 308, "刮": 309, "到": 310, "制": 311, "刷": 312, "券": 313, "刺": 314, "刻": 315, "則": 316, "前": 317, "剎": 318, "剔": 319, "剛": 320, "剝": 321, "剩": 322, "剪": 323, "副": 324, "割": 325, "創": 326, "剷": 327, "劃": 328, "劇": 329, "劉": 330, "劊": 331, "劍": 332, "劑": 333, "劖": 334, "力": 335, "功": 336, "加": 337, "劣": 338, "助": 339, "努": 340, "勁": 341, "勃": 342, "勇": 343, "勉": 344, "勒": 345, "動": 346, "勘": 347, "務": 348, "勝": 349, "勞": 350, "勢": 351, "勤": 352, "勳": 353, "勵": 354, "勸": 355, "勻": 356, "勾": 357, "勿": 358, "包": 359, "匈": 360, "化": 361, "北": 362, "匙": 363, "匡": 364, "匯": 365, "匹": 366, "匿": 367, "區": 368, "十": 369, "千": 370, "升": 371, "午": 372, "半": 373, "卑": 374, "卒": 375, "卓": 376, "協": 377, "南": 378, "博": 379, "卜": 380, "卡": 381, "卦": 382, "卧": 383, "印": 384, "危": 385, "即": 386, "卵": 387, "卷": 388, "卸": 389, "卻": 390, "卿": 391, "厄": 392, "厘": 393, "厚": 394, "原": 395, "厥": 396, "厭": 397, "厲": 398, "厴": 399, "去": 400, "參": 401, "又": 402, "叉": 403, "及": 404, "友": 405, "反": 406, "叔": 407, "取": 408, "受": 409, "叛": 410, "叢": 411, "口": 412, "古": 413, "句": 414, "另": 415, "叨": 416, "只": 417, "叫": 418, "召": 419, "叭": 420, "叮": 421, "可": 422, "台": 423, "史": 424, "右": 425, "司": 426, "叻": 427, "吃": 428, "各": 429, "合": 430, "吉": 431, "吊": 432, "吋": 433, "同": 434, "名": 435, "后": 436, "吐": 437, "向": 438, "���": 439, "吖": 440, "君": 441, "吝": 442, "吞": 443, "吟": 444, "吠": 445, "否": 446, "吧": 447, "吩": 448, "含": 449, "吱": 450, "吳": 451, "吵": 452, "吶": 453, "吸": 454, "吹": 455, "吻": 456, "吼": 457, "吽": 458, "吾": 459, "呀": 460, "呂": 461, "呃": 462, "呆": 463, "呈": 464, "告": 465, "呎": 466, "呔": 467, "呢": 468, "周": 469, "呱": 470, "味": 471, "呷": 472, "呻": 473, "呼": 474, "命": 475, "咀": 476, "咁": 477, "咄": 478, "咇": 479, "咋": 480, "和": 481, "咐": 482, "咕": 483, "咖": 484, "咗": 485, "咦": 486, "咧": 487, "咩": 488, "咪": 489, "咬": 490, "咯": 491, "咳": 492, "咸": 493, "咽": 494, "咿": 495, "哀": 496, "品": 497, "哂": 498, "哄": 499, "哇": 500, "哈": 501, "哉": 502, "哋": 503, "响": 504, "哎": 505, "員": 506, "哣": 507, "哥": 508, "哦": 509, "哨": 510, "哩": 511, "哪": 512, "哭": 513, "哲": 514, "哺": 515, "哼": 516, "唇": 517, "唈": 518, "唉": 519, "唎": 520, "唏": 521, "唐": 522, "唔": 523, "唞": 524, "唥": 525, "唧": 526, "唪": 527, "售": 528, "唯": 529, "唱": 530, "唸": 531, "啄": 532, "啅": 533, "商": 534, "啊": 535, "啋": 536, "問": 537, "啕": 538, "啖": 539, "啜": 540, "啞": 541, "啟": 542, "啡": 543, "啤": 544, "啦": 545, "啩": 546, "啪": 547, "啫": 548, "啱": 549, "啲": 550, "啵": 551, "喀": 552, "喂": 553, "喃": 554, "善": 555, "喇": 556, "喉": 557, "喊": 558, "喎": 559, "喐": 560, "喔": 561, "喙": 562, "喚": 563, "喜": 564, "喝": 565, "喪": 566, "喫": 567, "喬": 568, "單": 569, "喱": 570, "喳": 571, "喺": 572, "喻": 573, "喼": 574, "嗅": 575, "嗇": 576, "嗌": 577, "嗎": 578, "嗒": 579, "嗚": 580, "嗜": 581, "嗡": 582, "嗤": 583, "嗦": 584, "嗰": 585, "嗱": 586, "嗲": 587, "嗶": 588, "嗷": 589, "嗽": 590, "嘅": 591, "嘆": 592, "嘈": 593, "嘉": 594, "嘔": 595, "嘗": 596, "嘛": 597, "嘜": 598, "嘞": 599, "嘟": 600, "嘢": 601, "嘥": 602, "嘩": 603, "嘲": 604, "嘴": 605, "嘸": 606, "噁": 607, "噃": 608, "噄": 609, "噉": 610, "噌": 611, "噎": 612, "噏": 613, "噓": 614, "噚": 615, "噤": 616, "器": 617, "噪": 618, "噬": 619, "噴": 620, "噶": 621, "噹": 622, "嚇": 623, "嚎": 624, "嚐": 625, "嚕": 626, "嚟": 627, "嚡": 628, "嚢": 629, "嚥": 630, "嚨": 631, "嚴": 632, "嚷": 633, "嚼": 634, "嚿": 635, "囉": 636, "囊": 637, "囌": 638, "囍": 639, "囑": 640, "囚": 641, "四": 642, "囝": 643, "回": 644, "因": 645, "囡": 646, "囪": 647, "困": 648, "固": 649, "圃": 650, "圈": 651, "國": 652, "圍": 653, "圑": 654, "園": 655, "圓": 656, "圖": 657, "團": 658, "土": 659, "在": 660, "圭": 661, "地": 662, "圳": 663, "圾": 664, "址": 665, "均": 666, "坊": 667, "坎": 668, "坐": 669, "坑": 670, "坡": 671, "坤": 672, "坦": 673, "坪": 674, "坭": 675, "坳": 676, "垂": 677, "垃": 678, "型": 679, "垢": 680, "埃": 681, "埋": 682, "城": 683, "埔": 684, "埗": 685, "埞": 686, "域": 687, "埠": 688, "埲": 689, "執": 690, "培": 691, "基": 692, "堂": 693, "堅": 694, "堆": 695, "堡": 696, "堤": 697, "堪": 698, "報": 699, "場": 700, "堵": 701, "塊": 702, "塑": 703, "塔": 704, "塗": 705, "塘": 706, "塞": 707, "塢": 708, "填": 709, "塱": 710, "塵": 711, "塾": 712, "境": 713, "墅": 714, "墊": 715, "墓": 716, "墜": 717, "增": 718, "墟": 719, "墨": 720, "墩": 721, "墮": 722, "墳": 723, "壁": 724, "壆": 725, "壇": 726, "壓": 727, "壘": 728, "壞": 729, "壟": 730, "壩": 731, "士": 732, "壯": 733, "壹": 734, "壺": 735, "壽": 736, "夏": 737, "夕": 738, "外": 739, "多": 740, "夜": 741, "夠": 742, "夢": 743, "夥": 744, "大": 745, "天": 746, "太": 747, "夫": 748, "央": 749, "失": 750, "夷": 751, "夾": 752, "奀": 753, "奄": 754, "奇": 755, "奈": 756, "奉": 757, "奏": 758, "契": 759, "奔": 760, "奕": 761, "套": 762, "奚": 763, "奧": 764, "奪": 765, "奮": 766, "女": 767, "奴": 768, "奶": 769, "奸": 770, "她": 771, "好": 772, "如": 773, "妄": 774, "妒": 775, "妓": 776, "妙": 777, "妝": 778, "妥": 779, "妨": 780, "妳": 781, "妹": 782, "妻": 783, "姆": 784, "姊": 785, "始": 786, "姐": 787, "姑": 788, "姓": 789, "委": 790, "姣": 791, "姦": 792, "姨": 793, "姬": 794, "姻": 795, "姿": 796, "威": 797, "娃": 798, "娘": 799, "娛": 800, "娜": 801, "娥": 802, "娶": 803, "婆": 804, "婚": 805, "婦": 806, "媒": 807, "媽": 808, "媾": 809, "嫁": 810, "嫂": 811, "嫉": 812, "嫌": 813, "嫩": 814, "嫪": 815, "嫲": 816, "嫻": 817, "嬉": 818, "嬲": 819, "嬸": 820, "子": 821, "孔": 822, "孖": 823, "字": 824, "存": 825, "孚": 826, "孝": 827, "孟": 828, "季": 829, "孤": 830, "孥": 831, "孩": 832, "孫": 833, "孭": 834, "孰": 835, "孱": 836, "學": 837, "孽": 838, "它": 839, "宅": 840, "宇": 841, "守": 842, "安": 843, "宋": 844, "完": 845, "宏": 846, "宗": 847, "官": 848, "宙": 849, "定": 850, "宛": 851, "宜": 852, "客": 853, "宣": 854, "室": 855, "宮": 856, "宰": 857, "害": 858, "宴": 859, "宵": 860, "家": 861, "宸": 862, "容": 863, "宿": 864, "寂": 865, "寃": 866, "寄": 867, "寅": 868, "密": 869, "寇": 870, "富": 871, "寒": 872, "寓": 873, "寞": 874, "察": 875, "寡": 876, "寢": 877, "實": 878, "寧": 879, "寨": 880, "審": 881, "寫": 882, "寬": 883, "寮": 884, "寶": 885, "寸": 886, "寺": 887, "封": 888, "射": 889, "將": 890, "專": 891, "尊": 892, "尋": 893, "對": 894, "導": 895, "小": 896, "少": 897, "尖": 898, "尚": 899, "尤": 900, "尬": 901, "就": 902, "尷": 903, "尺": 904, "尼": 905, "尾": 906, "尿": 907, "局": 908, "屁": 909, "居": 910, "屆": 911, "屈": 912, "屋": 913, "屌": 914, "屍": 915, "屎": 916, "屏": 917, "屑": 918, "展": 919, "屙": 920, "屠": 921, "層": 922, "履": 923, "屬": 924, "屯": 925, "山": 926, "屹": 927, "岀": 928, "岡": 929, "岩": 930, "岬": 931, "岳": 932, "岸": 933, "峒": 934, "峯": 935, "峰": 936, "島": 937, "峻": 938, "峽": 939, "崆": 940, "崇": 941, "崗": 942, "崙": 943, "崧": 944, "崩": 945, "嵌": 946, "嶄": 947, "嶙": 948, "嶺": 949, "嶼": 950, "巉": 951, "巒": 952, "川": 953, "州": 954, "巡": 955, "巢": 956, "工": 957, "左": 958, "巧": 959, "巨": 960, "巫": 961, "差": 962, "己": 963, "已": 964, "巴": 965, "巷": 966, "巾": 967, "市": 968, "布": 969, "帆": 970, "希": 971, "帖": 972, "帚": 973, "帝": 974, "帥": 975, "師": 976, "席": 977, "帳": 978, "帶": 979, "常": 980, "帽": 981, "幅": 982, "幕": 983, "幡": 984, "幢": 985, "幣": 986, "幫": 987, "干": 988, "平": 989, "年": 990, "幸": 991, "幹": 992, "幻": 993, "幼": 994, "幽": 995, "幾": 996, "庇": 997, "床": 998, "序": 999, "底": 1000, "店": 1001, "庚": 1002, "府": 1003, "度": 1004, "座": 1005, "庫": 1006, "庭": 1007, "庵": 1008, "庶": 1009, "康": 1010, "庸": 1011, "廁": 1012, "廂": 1013, "廈": 1014, "廉": 1015, "廊": 1016, "廖": 1017, "廚": 1018, "廟": 1019, "廠": 1020, "廢": 1021, "廣": 1022, "廬": 1023, "廳": 1024, "延": 1025, "廷": 1026, "建": 1027, "廿": 1028, "弄": 1029, "弊": 1030, "弍": 1031, "式": 1032, "弓": 1033, "引": 1034, "弟": 1035, "弱": 1036, "張": 1037, "強": 1038, "弸": 1039, "强": 1040, "弼": 1041, "彈": 1042, "彌": 1043, "彎": 1044, "彗": 1045, "彙": 1046, "形": 1047, "彤": 1048, "彥": 1049, "彩": 1050, "彪": 1051, "彭": 1052, "影": 1053, "彷": 1054, "役": 1055, "彼": 1056, "彿": 1057, "往": 1058, "征": 1059, "待": 1060, "徇": 1061, "很": 1062, "徊": 1063, "律": 1064, "後": 1065, "徐": 1066, "徑": 1067, "徒": 1068, "得": 1069, "徘": 1070, "從": 1071, "御": 1072, "復": 1073, "循": 1074, "微": 1075, "徵": 1076, "德": 1077, "徹": 1078, "徽": 1079, "心": 1080, "必": 1081, "忌": 1082, "忍": 1083, "志": 1084, "忘": 1085, "忙": 1086, "忠": 1087, "快": 1088, "念": 1089, "忽": 1090, "忿": 1091, "怎": 1092, "怒": 1093, "怕": 1094, "思": 1095, "怡": 1096, "急": 1097, "怦": 1098, "性": 1099, "怨": 1100, "怪": 1101, "怯": 1102, "恃": 1103, "恆": 1104, "恐": 1105, "恒": 1106, "恕": 1107, "恙": 1108, "恢": 1109, "恤": 1110, "恥": 1111, "恨": 1112, "恩": 1113, "恭": 1114, "息": 1115, "恰": 1116, "悅": 1117, "悉": 1118, "悒": 1119, "悔": 1120, "悖": 1121, "悗": 1122, "悟": 1123, "悠": 1124, "患": 1125, "您": 1126, "悲": 1127, "悶": 1128, "情": 1129, "惇": 1130, "惑": 1131, "惘": 1132, "惜": 1133, "惟": 1134, "惠": 1135, "惡": 1136, "惦": 1137, "惰": 1138, "惱": 1139, "想": 1140, "惶": 1141, "惹": 1142, "愁": 1143, "愈": 1144, "愉": 1145, "意": 1146, "愚": 1147, "愛": 1148, "感": 1149, "愧": 1150, "慈": 1151, "態": 1152, "慌": 1153, "慎": 1154, "慕": 1155, "慘": 1156, "慚": 1157, "慢": 1158, "慣": 1159, "慤": 1160, "慧": 1161, "慨": 1162, "慮": 1163, "慰": 1164, "慳": 1165, "慶": 1166, "慷": 1167, "慾": 1168, "憂": 1169, "憎": 1170, "憐": 1171, "憑": 1172, "憚": 1173, "憤": 1174, "憧": 1175, "憩": 1176, "憫": 1177, "憬": 1178, "憶": 1179, "憾": 1180, "懂": 1181, "懇": 1182, "應": 1183, "懊": 1184, "懞": 1185, "懣": 1186, "懵": 1187, "懶": 1188, "懷": 1189, "懺": 1190, "懼": 1191, "懿": 1192, "戀": 1193, "戇": 1194, "戊": 1195, "戎": 1196, "成": 1197, "我": 1198, "戒": 1199, "戕": 1200, "或": 1201, "戚": 1202, "戟": 1203, "戥": 1204, "截": 1205, "戰": 1206, "戲": 1207, "戴": 1208, "戶": 1209, "戽": 1210, "戾": 1211, "房": 1212, "所": 1213, "扂": 1214, "扇": 1215, "手": 1216, "才": 1217, "扎": 1218, "扑": 1219, "扒": 1220, "打": 1221, "托": 1222, "扣": 1223, "扭": 1224, "扮": 1225, "扯": 1226, "扶": 1227, "批": 1228, "扻": 1229, "扼": 1230, "找": 1231, "承": 1232, "技": 1233, "抄": 1234, "抆": 1235, "把": 1236, "抑": 1237, "抓": 1238, "投": 1239, "抖": 1240, "抗": 1241, "折": 1242, "抦": 1243, "抬": 1244, "抱": 1245, "抵": 1246, "抹": 1247, "押": 1248, "抽": 1249, "抿": 1250, "拂": 1251, "拃": 1252, "拆": 1253, "拉": 1254, "拋": 1255, "拌": 1256, "拍": 1257, "拎": 1258, "拐": 1259, "拒": 1260, "拓": 1261, "拔": 1262, "拖": 1263, "拗": 1264, "拘": 1265, "拙": 1266, "招": 1267, "拜": 1268, "括": 1269, "拮": 1270, "拯": 1271, "拱": 1272, "拳": 1273, "拼": 1274, "拾": 1275, "拿": 1276, "持": 1277, "指": 1278, "挈": 1279, "按": 1280, "挑": 1281, "挖": 1282, "挨": 1283, "挪": 1284, "挫": 1285, "振": 1286, "挺": 1287, "挽": 1288, "挾": 1289, "捉": 1290, "捋": 1291, "捌": 1292, "捐": 1293, "捕": 1294, "捨": 1295, "捩": 1296, "据": 1297, "捱": 1298, "捲": 1299, "捶": 1300, "捷": 1301, "捺": 1302, "捽": 1303, "掂": 1304, "掃": 1305, "掅": 1306, "授": 1307, "掉": 1308, "掌": 1309, "排": 1310, "掕": 1311, "掗": 1312, "掘": 1313, "掙": 1314, "掛": 1315, "掟": 1316, "掠": 1317, "採": 1318, "探": 1319, "掣": 1320, "接": 1321, "控": 1322, "推": 1323, "掩": 1324, "措": 1325, "揀": 1326, "揇": 1327, "揈": 1328, "揉": 1329, "提": 1330, "插": 1331, "揗": 1332, "揚": 1333, "換": 1334, "揞": 1335, "握": 1336, "揣": 1337, "揦": 1338, "揩": 1339, "揪": 1340, "揭": 1341, "揮": 1342, "揳": 1343, "援": 1344, "揸": 1345, "揼": 1346, "揾": 1347, "損": 1348, "搏": 1349, "搖": 1350, "搗": 1351, "搜": 1352, "搞": 1353, "搣": 1354, "搬": 1355, "搭": 1356, "搵": 1357, "搶": 1358, "搽": 1359, "摑": 1360, "摘": 1361, "摙": 1362, "摞": 1363, "摧": 1364, "摩": 1365, "摯": 1366, "摳": 1367, "摷": 1368, "摸": 1369, "摺": 1370, "撇": 1371, "撈": 1372, "撐": 1373, "撒": 1374, "撓": 1375, "撕": 1376, "撚": 1377, "撞": 1378, "撤": 1379, "撥": 1380, "撩": 1381, "撫": 1382, "播": 1383, "撮": 1384, "撲": 1385, "撳": 1386, "撻": 1387, "撼": 1388, "撿": 1389, "擁": 1390, "擂": 1391, "擅": 1392, "擇": 1393, "擊": 1394, "擋": 1395, "操": 1396, "擎": 1397, "擒": 1398, "擔": 1399, "擘": 1400, "據": 1401, "擤": 1402, "擦": 1403, "擬": 1404, "擰": 1405, "擲": 1406, "擴": 1407, "擸": 1408, "擺": 1409, "擾": 1410, "攀": 1411, "攋": 1412, "攏": 1413, "攔": 1414, "攘": 1415, "攝": 1416, "攞": 1417, "攣": 1418, "攤": 1419, "攪": 1420, "攬": 1421, "支": 1422, "攰": 1423, "收": 1424, "攸": 1425, "改": 1426, "攻": 1427, "放": 1428, "政": 1429, "故": 1430, "效": 1431, "敏": 1432, "救": 1433, "敗": 1434, "敘": 1435, "教": 1436, "敝": 1437, "敢": 1438, "散": 1439, "敦": 1440, "敬": 1441, "敲": 1442, "整": 1443, "敵": 1444, "敷": 1445, "數": 1446, "斂": 1447, "斃": 1448, "文": 1449, "斐": 1450, "斑": 1451, "斗": 1452, "料": 1453, "斜": 1454, "斟": 1455, "斤": 1456, "斧": 1457, "斬": 1458, "斯": 1459, "新": 1460, "斷": 1461, "方": 1462, "於": 1463, "施": 1464, "旁": 1465, "旅": 1466, "旋": 1467, "族": 1468, "旗": 1469, "既": 1470, "旣": 1471, "日": 1472, "旦": 1473, "旨": 1474, "早": 1475, "旬": 1476, "旭": 1477, "旳": 1478, "旺": 1479, "昂": 1480, "昃": 1481, "昆": 1482, "昇": 1483, "昌": 1484, "明": 1485, "昏": 1486, "昐": 1487, "易": 1488, "昔": 1489, "星": 1490, "映": 1491, "春": 1492, "昧": 1493, "昨": 1494, "昭": 1495, "是": 1496, "昺": 1497, "時": 1498, "晃": 1499, "晉": 1500, "晌": 1501, "晏": 1502, "晒": 1503, "晚": 1504, "晝": 1505, "晤": 1506, "晨": 1507, "普": 1508, "景": 1509, "晴": 1510, "晶": 1511, "智": 1512, "晾": 1513, "暇": 1514, "暈": 1515, "暉": 1516, "暑": 1517, "暖": 1518, "暗": 1519, "暢": 1520, "暨": 1521, "暫": 1522, "暮": 1523, "暴": 1524, "暸": 1525, "曆": 1526, "曉": 1527, "曖": 1528, "曜": 1529, "曬": 1530, "曱": 1531, "曲": 1532, "曳": 1533, "更": 1534, "書": 1535, "曹": 1536, "曼": 1537, "曾": 1538, "替": 1539, "最": 1540, "會": 1541, "月": 1542, "有": 1543, "朋": 1544, "服": 1545, "朕": 1546, "朗": 1547, "望": 1548, "朝": 1549, "期": 1550, "朦": 1551, "朧": 1552, "木": 1553, "未": 1554, "末": 1555, "本": 1556, "札": 1557, "朱": 1558, "朴": 1559, "朵": 1560, "朽": 1561, "杆": 1562, "杉": 1563, "李": 1564, "杏": 1565, "材": 1566, "村": 1567, "杖": 1568, "杜": 1569, "杞": 1570, "束": 1571, "来": 1572, "杭": 1573, "杯": 1574, "杰": 1575, "東": 1576, "杷": 1577, "松": 1578, "板": 1579, "枇": 1580, "枉": 1581, "枕": 1582, "林": 1583, "枚": 1584, "果": 1585, "枝": 1586, "枯": 1587, "枱": 1588, "架": 1589, "柄": 1590, "柏": 1591, "某": 1592, "柑": 1593, "柒": 1594, "染": 1595, "柔": 1596, "柚": 1597, "柞": 1598, "查": 1599, "柯": 1600, "柱": 1601, "柳": 1602, "柴": 1603, "柵": 1604, "柺": 1605, "柿": 1606, "栗": 1607, "校": 1608, "栢": 1609, "核": 1610, "根": 1611, "格": 1612, "栽": 1613, "桂": 1614, "桃": 1615, "桅": 1616, "案": 1617, "桌": 1618, "桐": 1619, "桑": 1620, "桔": 1621, "桶": 1622, "桿": 1623, "梁": 1624, "梅": 1625, "梓": 1626, "梗": 1627, "梘": 1628, "條": 1629, "梧": 1630, "梨": 1631, "梯": 1632, "械": 1633, "梳": 1634, "梵": 1635, "棄": 1636, "棉": 1637, "棋": 1638, "棍": 1639, "棒": 1640, "棕": 1641, "棖": 1642, "棗": 1643, "棘": 1644, "棚": 1645, "棟": 1646, "棠": 1647, "棧": 1648, "森": 1649, "棲": 1650, "棺": 1651, "椅": 1652, "植": 1653, "椏": 1654, "椒": 1655, "椰": 1656, "楂": 1657, "楊": 1658, "楋": 1659, "楓": 1660, "楚": 1661, "楣": 1662, "業": 1663, "極": 1664, "概": 1665, "榆": 1666, "榕": 1667, "榚": 1668, "榛": 1669, "榜": 1670, "榨": 1671, "榮": 1672, "榴": 1673, "構": 1674, "槍": 1675, "槐": 1676, "槤": 1677, "槽": 1678, "樂": 1679, "樊": 1680, "樑": 1681, "樓": 1682, "標": 1683, "樞": 1684, "樟": 1685, "模": 1686, "樣": 1687, "樸": 1688, "樹": 1689, "樺": 1690, "樽": 1691, "橋": 1692, "橘": 1693, "橙": 1694, "機": 1695, "橡": 1696, "橢": 1697, "橫": 1698, "檀": 1699, "檔": 1700, "檢": 1701, "檬": 1702, "檯": 1703, "檳": 1704, "檸": 1705, "檻": 1706, "櫃": 1707, "櫈": 1708, "櫚": 1709, "櫸": 1710, "櫻": 1711, "欄": 1712, "權": 1713, "欖": 1714, "欠": 1715, "次": 1716, "欣": 1717, "欲": 1718, "欺": 1719, "欽": 1720, "款": 1721, "歇": 1722, "歉": 1723, "歌": 1724, "歎": 1725, "歐": 1726, "歛": 1727, "歡": 1728, "止": 1729, "正": 1730, "此": 1731, "步": 1732, "武": 1733, "歧": 1734, "歪": 1735, "歲": 1736, "歷": 1737, "歸": 1738, "歹": 1739, "死": 1740, "殄": 1741, "殆": 1742, "殊": 1743, "殖": 1744, "殘": 1745, "殮": 1746, "段": 1747, "殷": 1748, "殺": 1749, "殼": 1750, "殿": 1751, "毀": 1752, "毅": 1753, "毋": 1754, "母": 1755, "每": 1756, "毒": 1757, "毓": 1758, "比": 1759, "毛": 1760, "毡": 1761, "毫": 1762, "氏": 1763, "民": 1764, "氓": 1765, "氛": 1766, "氣": 1767, "氧": 1768, "氯": 1769, "水": 1770, "永": 1771, "氹": 1772, "汀": 1773, "汁": 1774, "求": 1775, "汕": 1776, "汗": 1777, "汝": 1778, "江": 1779, "池": 1780, "污": 1781, "汪": 1782, "汰": 1783, "汶": 1784, "決": 1785, "汽": 1786, "沃": 1787, "沈": 1788, "沉": 1789, "沐": 1790, "沒": 1791, "沖": 1792, "沙": 1793, "沛": 1794, "沫": 1795, "沮": 1796, "沱": 1797, "河": 1798, "油": 1799, "治": 1800, "沽": 1801, "沾": 1802, "沿": 1803, "況": 1804, "泄": 1805, "泉": 1806, "泊": 1807, "泌": 1808, "泓": 1809, "法": 1810, "泛": 1811, "泡": 1812, "波": 1813, "泥": 1814, "注": 1815, "泮": 1816, "泰": 1817, "泳": 1818, "洋": 1819, "洗": 1820, "洛": 1821, "洞": 1822, "津": 1823, "洪": 1824, "洱": 1825, "洲": 1826, "洶": 1827, "活": 1828, "洽": 1829, "派": 1830, "流": 1831, "浙": 1832, "浚": 1833, "浣": 1834, "浦": 1835, "浩": 1836, "浪": 1837, "浮": 1838, "浴": 1839, "海": 1840, "浸": 1841, "涂": 1842, "消": 1843, "涉": 1844, "涌": 1845, "涕": 1846, "涯": 1847, "液": 1848, "涷": 1849, "涼": 1850, "淋": 1851, "淒": 1852, "淘": 1853, "淚": 1854, "淡": 1855, "淥": 1856, "淨": 1857, "淩": 1858, "淪": 1859, "淫": 1860, "深": 1861, "混": 1862, "淸": 1863, "淺": 1864, "添": 1865, "清": 1866, "減": 1867, "渝": 1868, "渠": 1869, "渡": 1870, "渣": 1871, "渦": 1872, "温": 1873, "測": 1874, "渭": 1875, "港": 1876, "渴": 1877, "游": 1878, "渺": 1879, "渾": 1880, "湃": 1881, "湖": 1882, "湘": 1883, "湧": 1884, "湯": 1885, "溋": 1886, "源": 1887, "準": 1888, "溜": 1889, "溝": 1890, "溢": 1891, "溪": 1892, "溫": 1893, "溶": 1894, "滂": 1895, "滄": 1896, "滅": 1897, "滋": 1898, "滌": 1899, "滑": 1900, "滔": 1901, "滘": 1902, "滙": 1903, "滯": 1904, "滷": 1905, "滾": 1906, "滿": 1907, "漁": 1908, "漂": 1909, "漆": 1910, "漏": 1911, "漓": 1912, "演": 1913, "漠": 1914, "漢": 1915, "漫": 1916, "漬": 1917, "漲": 1918, "漸": 1919, "漾": 1920, "漿": 1921, "潑": 1922, "潔": 1923, "潛": 1924, "潤": 1925, "潭": 1926, "潮": 1927, "潰": 1928, "潲": 1929, "潷": 1930, "潺": 1931, "澄": 1932, "澍": 1933, "澎": 1934, "澡": 1935, "澤": 1936, "澩": 1937, "澱": 1938, "澳": 1939, "激": 1940, "濃": 1941, "濕": 1942, "濛": 1943, "濟": 1944, "濠": 1945, "濤": 1946, "濫": 1947, "濱": 1948, "濾": 1949, "瀉": 1950, "瀚": 1951, "瀝": 1952, "瀟": 1953, "瀨": 1954, "瀾": 1955, "灑": 1956, "灘": 1957, "灣": 1958, "火": 1959, "灰": 1960, "灼": 1961, "災": 1962, "炆": 1963, "炊": 1964, "炎": 1965, "炒": 1966, "炕": 1967, "炙": 1968, "炭": 1969, "炮": 1970, "炳": 1971, "炸": 1972, "為": 1973, "烈": 1974, "烏": 1975, "烘": 1976, "烙": 1977, "烟": 1978, "烤": 1979, "烹": 1980, "焉": 1981, "焗": 1982, "焚": 1983, "無": 1984, "焦": 1985, "然": 1986, "煉": 1987, "煎": 1988, "煖": 1989, "煙": 1990, "煞": 1991, "煤": 1992, "照": 1993, "煨": 1994, "煩": 1995, "煮": 1996, "煲": 1997, "煽": 1998, "熄": 1999, "熊": 2000, "熒": 2001, "熔": 2002, "熙": 2003, "熟": 2004, "熬": 2005, "熱": 2006, "熾": 2007, "燃": 2008, "燈": 2009, "燉": 2010, "燒": 2011, "燕": 2012, "燜": 2013, "營": 2014, "燥": 2015, "燭": 2016, "燴": 2017, "燶": 2018, "爆": 2019, "爐": 2020, "爛": 2021, "爪": 2022, "爬": 2023, "爭": 2024, "爲": 2025, "爵": 2026, "父": 2027, "爸": 2028, "爹": 2029, "爺": 2030, "爽": 2031, "爾": 2032, "牀": 2033, "牆": 2034, "片": 2035, "版": 2036, "牌": 2037, "牘": 2038, "牙": 2039, "牛": 2040, "牡": 2041, "牢": 2042, "牧": 2043, "物": 2044, "牯": 2045, "牲": 2046, "特": 2047, "牽": 2048, "犀": 2049, "犧": 2050, "犬": 2051, "犯": 2052, "狀": 2053, "狂": 2054, "狄": 2055, "狐": 2056, "狗": 2057, "狠": 2058, "狡": 2059, "狩": 2060, "狸": 2061, "狹": 2062, "狼": 2063, "猄": 2064, "猛": 2065, "猜": 2066, "猴": 2067, "猶": 2068, "猾": 2069, "獄": 2070, "獅": 2071, "獎": 2072, "獠": 2073, "獨": 2074, "獲": 2075, "獵": 2076, "獸": 2077, "獻": 2078, "玄": 2079, "率": 2080, "玉": 2081, "王": 2082, "玟": 2083, "玩": 2084, "玫": 2085, "玻": 2086, "珀": 2087, "珊": 2088, "珍": 2089, "珏": 2090, "珒": 2091, "珠": 2092, "班": 2093, "現": 2094, "球": 2095, "理": 2096, "琉": 2097, "琛": 2098, "琦": 2099, "琳": 2100, "琴": 2101, "琵": 2102, "琶": 2103, "瑕": 2104, "瑙": 2105, "瑜": 2106, "瑞": 2107, "瑟": 2108, "瑤": 2109, "瑧": 2110, "瑪": 2111, "瑰": 2112, "璀": 2113, "璃": 2114, "璇": 2115, "璉": 2116, "璐": 2117, "璟": 2118, "璧": 2119, "璨": 2120, "環": 2121, "璵": 2122, "璽": 2123, "瓊": 2124, "瓏": 2125, "瓜": 2126, "瓦": 2127, "瓶": 2128, "甘": 2129, "甚": 2130, "甜": 2131, "生": 2132, "產": 2133, "甥": 2134, "用": 2135, "甩": 2136, "甫": 2137, "田": 2138, "由": 2139, "甲": 2140, "申": 2141, "甴": 2142, "男": 2143, "甸": 2144, "畀": 2145, "畋": 2146, "界": 2147, "畏": 2148, "畐": 2149, "畔": 2150, "留": 2151, "畜": 2152, "畢": 2153, "略": 2154, "番": 2155, "畫": 2156, "異": 2157, "當": 2158, "畿": 2159, "疆": 2160, "疇": 2161, "疊": 2162, "疏": 2163, "疑": 2164, "疤": 2165, "疫": 2166, "疲": 2167, "疵": 2168, "疹": 2169, "疼": 2170, "疾": 2171, "病": 2172, "症": 2173, "痕": 2174, "痛": 2175, "痢": 2176, "痰": 2177, "痱": 2178, "痴": 2179, "痺": 2180, "痾": 2181, "瘀": 2182, "瘁": 2183, "瘋": 2184, "瘓": 2185, "瘟": 2186, "瘡": 2187, "瘦": 2188, "療": 2189, "癆": 2190, "癌": 2191, "癡": 2192, "癢": 2193, "癩": 2194, "癮": 2195, "癱": 2196, "癲": 2197, "登": 2198, "發": 2199, "白": 2200, "百": 2201, "皂": 2202, "的": 2203, "皆": 2204, "皇": 2205, "皚": 2206, "皮": 2207, "皺": 2208, "盃": 2209, "盅": 2210, "盆": 2211, "盈": 2212, "益": 2213, "盏": 2214, "盒": 2215, "盔": 2216, "盛": 2217, "盜": 2218, "盞": 2219, "盟": 2220, "盡": 2221, "監": 2222, "盤": 2223, "盧": 2224, "盪": 2225, "目": 2226, "盲": 2227, "直": 2228, "相": 2229, "盼": 2230, "盾": 2231, "省": 2232, "眉": 2233, "看": 2234, "眞": 2235, "真": 2236, "眠": 2237, "眨": 2238, "眯": 2239, "眶": 2240, "眼": 2241, "眾": 2242, "着": 2243, "睄": 2244, "睇": 2245, "睏": 2246, "睛": 2247, "睜": 2248, "睡": 2249, "督": 2250, "睥": 2251, "睦": 2252, "睨": 2253, "睬": 2254, "睹": 2255, "瞅": 2256, "瞌": 2257, "瞓": 2258, "瞞": 2259, "瞬": 2260, "瞭": 2261, "矛": 2262, "知": 2263, "矩": 2264, "短": 2265, "矮": 2266, "石": 2267, "砂": 2268, "砌": 2269, "砍": 2270, "研": 2271, "砰": 2272, "砲": 2273, "破": 2274, "砵": 2275, "砸": 2276, "硤": 2277, "硬": 2278, "碇": 2279, "碉": 2280, "碌": 2281, "碎": 2282, "碑": 2283, "碗": 2284, "碘": 2285, "碟": 2286, "碧": 2287, "碰": 2288, "確": 2289, "碼": 2290, "磅": 2291, "磐": 2292, "磚": 2293, "磡": 2294, "磨": 2295, "磯": 2296, "礎": 2297, "礙": 2298, "礦": 2299, "礫": 2300, "示": 2301, "社": 2302, "祈": 2303, "祐": 2304, "祖": 2305, "祝": 2306, "神": 2307, "祟": 2308, "祠": 2309, "祥": 2310, "票": 2311, "祭": 2312, "祿": 2313, "禁": 2314, "禍": 2315, "福": 2316, "禡": 2317, "禧": 2318, "禪": 2319, "禮": 2320, "禱": 2321, "禽": 2322, "禾": 2323, "秀": 2324, "私": 2325, "秅": 2326, "秉": 2327, "秋": 2328, "科": 2329, "秒": 2330, "秘": 2331, "租": 2332, "秤": 2333, "秦": 2334, "秧": 2335, "秩": 2336, "移": 2337, "稀": 2338, "稅": 2339, "稈": 2340, "程": 2341, "稍": 2342, "稔": 2343, "稚": 2344, "稠": 2345, "種": 2346, "稱": 2347, "稻": 2348, "稿": 2349, "穀": 2350, "穌": 2351, "積": 2352, "穎": 2353, "穗": 2354, "穢": 2355, "穩": 2356, "穫": 2357, "穴": 2358, "究": 2359, "空": 2360, "穿": 2361, "突": 2362, "窄": 2363, "窒": 2364, "窗": 2365, "窠": 2366, "窩": 2367, "窮": 2368, "窰": 2369, "窿": 2370, "竄": 2371, "竅": 2372, "竇": 2373, "竊": 2374, "立": 2375, "站": 2376, "竟": 2377, "章": 2378, "童": 2379, "端": 2380, "競": 2381, "竹": 2382, "笆": 2383, "笈": 2384, "笏": 2385, "笑": 2386, "笛": 2387, "笠": 2388, "符": 2389, "笨": 2390, "笪": 2391, "第": 2392, "筆": 2393, "等": 2394, "筋": 2395, "筍": 2396, "筏": 2397, "筒": 2398, "答": 2399, "策": 2400, "筲": 2401, "筵": 2402, "筷": 2403, "箋": 2404, "箍": 2405, "箕": 2406, "算": 2407, "管": 2408, "箭": 2409, "箱": 2410, "箴": 2411, "節": 2412, "範": 2413, "篇": 2414, "築": 2415, "篋": 2416, "篙": 2417, "篤": 2418, "篳": 2419, "簍": 2420, "簡": 2421, "簽": 2422, "簾": 2423, "簿": 2424, "籃": 2425, "籌": 2426, "籍": 2427, "籐": 2428, "籠": 2429, "籤": 2430, "籬": 2431, "籮": 2432, "籲": 2433, "米": 2434, "籽": 2435, "粉": 2436, "粒": 2437, "粗": 2438, "粟": 2439, "粥": 2440, "粳": 2441, "粵": 2442, "粹": 2443, "粼": 2444, "精": 2445, "粿": 2446, "糉": 2447, "糊": 2448, "糍": 2449, "糕": 2450, "糖": 2451, "糞": 2452, "糟": 2453, "糧": 2454, "糯": 2455, "糰": 2456, "糴": 2457, "系": 2458, "糾": 2459, "紀": 2460, "約": 2461, "紅": 2462, "納": 2463, "紐": 2464, "紓": 2465, "純": 2466, "紗": 2467, "紙": 2468, "級": 2469, "紛": 2470, "素": 2471, "索": 2472, "紥": 2473, "紫": 2474, "紮": 2475, "累": 2476, "細": 2477, "紳": 2478, "紹": 2479, "終": 2480, "組": 2481, "結": 2482, "絕": 2483, "絞": 2484, "絡": 2485, "給": 2486, "絨": 2487, "統": 2488, "絲": 2489, "絶": 2490, "綁": 2491, "經": 2492, "綜": 2493, "綠": 2494, "綫": 2495, "維": 2496, "網": 2497, "綿": 2498, "緊": 2499, "緒": 2500, "緘": 2501, "線": 2502, "緣": 2503, "編": 2504, "緩": 2505, "緬": 2506, "練": 2507, "緻": 2508, "縉": 2509, "縊": 2510, "縛": 2511, "縫": 2512, "縮": 2513, "縱": 2514, "縷": 2515, "總": 2516, "績": 2517, "繁": 2518, "織": 2519, "繞": 2520, "繩": 2521, "繫": 2522, "繳": 2523, "繼": 2524, "續": 2525, "纏": 2526, "纔": 2527, "纖": 2528, "纜": 2529, "缸": 2530, "缺": 2531, "缽": 2532, "罅": 2533, "罐": 2534, "罔": 2535, "罕": 2536, "罟": 2537, "罩": 2538, "罪": 2539, "置": 2540, "罰": 2541, "署": 2542, "罵": 2543, "罷": 2544, "羅": 2545, "羈": 2546, "羊": 2547, "羌": 2548, "美": 2549, "羞": 2550, "羣": 2551, "群": 2552, "義": 2553, "羲": 2554, "羹": 2555, "羽": 2556, "翁": 2557, "翅": 2558, "翌": 2559, "習": 2560, "翔": 2561, "翠": 2562, "翡": 2563, "翩": 2564, "翰": 2565, "翱": 2566, "翻": 2567, "翼": 2568, "耀": 2569, "老": 2570, "考": 2571, "者": 2572, "而": 2573, "耍": 2574, "耐": 2575, "耕": 2576, "耗": 2577, "耘": 2578, "耳": 2579, "耶": 2580, "耷": 2581, "聆": 2582, "聊": 2583, "聖": 2584, "聘": 2585, "聚": 2586, "聞": 2587, "聯": 2588, "聰": 2589, "聲": 2590, "聳": 2591, "聶": 2592, "職": 2593, "聽": 2594, "肅": 2595, "肆": 2596, "肇": 2597, "肉": 2598, "肋": 2599, "肌": 2600, "肓": 2601, "肖": 2602, "肘": 2603, "肚": 2604, "肛": 2605, "肝": 2606, "股": 2607, "肥": 2608, "肨": 2609, "肩": 2610, "肯": 2611, "育": 2612, "肴": 2613, "肺": 2614, "胃": 2615, "背": 2616, "胎": 2617, "胚": 2618, "胡": 2619, "胭": 2620, "胸": 2621, "胺": 2622, "能": 2623, "脂": 2624, "脅": 2625, "脆": 2626, "脈": 2627, "脊": 2628, "脫": 2629, "脷": 2630, "脹": 2631, "脾": 2632, "腋": 2633, "腍": 2634, "腎": 2635, "腐": 2636, "腔": 2637, "腕": 2638, "腥": 2639, "腦": 2640, "腩": 2641, "腫": 2642, "腰": 2643, "腳": 2644, "腸": 2645, "腺": 2646, "腿": 2647, "膀": 2648, "膊": 2649, "膏": 2650, "膚": 2651, "膜": 2652, "膝": 2653, "膠": 2654, "膨": 2655, "膩": 2656, "膳": 2657, "膺": 2658, "膽": 2659, "臂": 2660, "臉": 2661, "臘": 2662, "臟": 2663, "臣": 2664, "臨": 2665, "自": 2666, "臭": 2667, "至": 2668, "致": 2669, "臺": 2670, "臻": 2671, "臼": 2672, "舂": 2673, "舅": 2674, "與": 2675, "興": 2676, "舉": 2677, "舊": 2678, "舌": 2679, "舍": 2680, "舐": 2681, "舒": 2682, "舔": 2683, "舖": 2684, "舞": 2685, "舟": 2686, "舢": 2687, "舨": 2688, "航": 2689, "般": 2690, "舶": 2691, "船": 2692, "艇": 2693, "艦": 2694, "良": 2695, "艱": 2696, "色": 2697, "艷": 2698, "芋": 2699, "芒": 2700, "芙": 2701, "芝": 2702, "芥": 2703, "芬": 2704, "芭": 2705, "芯": 2706, "花": 2707, "芳": 2708, "芹": 2709, "芽": 2710, "苑": 2711, "苔": 2712, "苗": 2713, "苟": 2714, "苣": 2715, "若": 2716, "苦": 2717, "英": 2718, "茂": 2719, "范": 2720, "茄": 2721, "茅": 2722, "茫": 2723, "茵": 2724, "茶": 2725, "茸": 2726, "荃": 2727, "草": 2728, "荊": 2729, "荒": 2730, "荔": 2731, "荷": 2732, "莆": 2733, "莉": 2734, "莊": 2735, "莎": 2736, "莓": 2737, "莞": 2738, "莫": 2739, "莽": 2740, "菁": 2741, "菇": 2742, "菊": 2743, "菌": 2744, "菓": 2745, "菜": 2746, "菠": 2747, "菩": 2748, "華": 2749, "菱": 2750, "菲": 2751, "菴": 2752, "萃": 2753, "萄": 2754, "萊": 2755, "萍": 2756, "萬": 2757, "萺": 2758, "落": 2759, "葉": 2760, "著": 2761, "葛": 2762, "葡": 2763, "董": 2764, "葫": 2765, "葬": 2766, "葳": 2767, "葵": 2768, "蒂": 2769, "蒙": 2770, "蒜": 2771, "蒡": 2772, "蒲": 2773, "蒸": 2774, "蒼": 2775, "蓀": 2776, "蓆": 2777, "蓉": 2778, "蓋": 2779, "蓓": 2780, "蓬": 2781, "蓮": 2782, "蓺": 2783, "蔓": 2784, "蔔": 2785, "蔗": 2786, "蔥": 2787, "蔫": 2788, "蔬": 2789, "蔭": 2790, "蔽": 2791, "蕃": 2792, "蕉": 2793, "蕎": 2794, "蕙": 2795, "蕩": 2796, "蕪": 2797, "蕭": 2798, "蕾": 2799, "薄": 2800, "薇": 2801, "薈": 2802, "薏": 2803, "薑": 2804, "薩": 2805, "薪": 2806, "薯": 2807, "薰": 2808, "藉": 2809, "藍": 2810, "藏": 2811, "藐": 2812, "藕": 2813, "藝": 2814, "藤": 2815, "藥": 2816, "藹": 2817, "蘅": 2818, "蘆": 2819, "蘇": 2820, "蘋": 2821, "蘑": 2822, "蘭": 2823, "蘸": 2824, "蘿": 2825, "虎": 2826, "虐": 2827, "虓": 2828, "處": 2829, "虛": 2830, "號": 2831, "虧": 2832, "虱": 2833, "虹": 2834, "蚊": 2835, "蚌": 2836, "蚝": 2837, "蚵": 2838, "蚺": 2839, "蛇": 2840, "蛋": 2841, "蛛": 2842, "蛟": 2843, "蛤": 2844, "蜂": 2845, "蜆": 2846, "蜊": 2847, "蜘": 2848, "蜜": 2849, "蜢": 2850, "蝕": 2851, "蝗": 2852, "蝦": 2853, "蝨": 2854, "蝴": 2855, "蝶": 2856, "蝸": 2857, "融": 2858, "螞": 2859, "螢": 2860, "螺": 2861, "蟀": 2862, "蟆": 2863, "蟋": 2864, "蟠": 2865, "蟬": 2866, "蟲": 2867, "蟹": 2868, "蟻": 2869, "蠅": 2870, "蠔": 2871, "蠟": 2872, "蠢": 2873, "蠱": 2874, "蠻": 2875, "血": 2876, "衆": 2877, "行": 2878, "衍": 2879, "術": 2880, "街": 2881, "衙": 2882, "衛": 2883, "衝": 2884, "衞": 2885, "衡": 2886, "衣": 2887, "表": 2888, "衫": 2889, "衰": 2890, "衲": 2891, "衷": 2892, "袁": 2893, "袋": 2894, "袖": 2895, "被": 2896, "裁": 2897, "裏": 2898, "裔": 2899, "裕": 2900, "裙": 2901, "補": 2902, "裝": 2903, "裡": 2904, "裴": 2905, "製": 2906, "複": 2907, "褒": 2908, "褦": 2909, "褪": 2910, "褲": 2911, "褸": 2912, "襟": 2913, "襪": 2914, "襯": 2915, "襲": 2916, "西": 2917, "要": 2918, "覆": 2919, "見": 2920, "規": 2921, "覓": 2922, "視": 2923, "親": 2924, "覲": 2925, "覺": 2926, "覽": 2927, "觀": 2928, "角": 2929, "解": 2930, "觸": 2931, "言": 2932, "訂": 2933, "計": 2934, "訊": 2935, "討": 2936, "訓": 2937, "訕": 2938, "託": 2939, "記": 2940, "訝": 2941, "訪": 2942, "設": 2943, "許": 2944, "訴": 2945, "診": 2946, "註": 2947, "証": 2948, "詆": 2949, "詐": 2950, "評": 2951, "詞": 2952, "詢": 2953, "試": 2954, "詩": 2955, "詭": 2956, "話": 2957, "該": 2958, "詳": 2959, "詹": 2960, "誅": 2961, "誇": 2962, "誌": 2963, "認": 2964, "誓": 2965, "誕": 2966, "誘": 2967, "語": 2968, "誠": 2969, "誡": 2970, "誤": 2971, "誨": 2972, "說": 2973, "説": 2974, "誰": 2975, "課": 2976, "誼": 2977, "調": 2978, "談": 2979, "請": 2980, "諒": 2981, "論": 2982, "諗": 2983, "諜": 2984, "諦": 2985, "諧": 2986, "諫": 2987, "諷": 2988, "諸": 2989, "諺": 2990, "諾": 2991, "謀": 2992, "謁": 2993, "謂": 2994, "謊": 2995, "謎": 2996, "謙": 2997, "講": 2998, "謝": 2999, "謢": 3000, "謬": 3001, "謹": 3002, "謾": 3003, "證": 3004, "譎": 3005, "譖": 3006, "識": 3007, "譚": 3008, "譜": 3009, "警": 3010, "譬": 3011, "譯": 3012, "議": 3013, "譴": 3014, "護": 3015, "譽": 3016, "讀": 3017, "變": 3018, "讎": 3019, "讓": 3020, "讚": 3021, "谷": 3022, "豁": 3023, "豂": 3024, "豆": 3025, "豈": 3026, "豉": 3027, "豎": 3028, "豐": 3029, "豚": 3030, "象": 3031, "豪": 3032, "豫": 3033, "豬": 3034, "豹": 3035, "貂": 3036, "貌": 3037, "貓": 3038, "貝": 3039, "負": 3040, "財": 3041, "貢": 3042, "貧": 3043, "貨": 3044, "販": 3045, "貪": 3046, "貫": 3047, "責": 3048, "貴": 3049, "貶": 3050, "買": 3051, "貸": 3052, "費": 3053, "貼": 3054, "貿": 3055, "賀": 3056, "賃": 3057, "資": 3058, "賈": 3059, "賊": 3060, "賒": 3061, "賓": 3062, "賜": 3063, "賞": 3064, "賢": 3065, "賣": 3066, "賤": 3067, "賦": 3068, "質": 3069, "賬": 3070, "賭": 3071, "賴": 3072, "賺": 3073, "購": 3074, "賽": 3075, "贅": 3076, "贈": 3077, "贊": 3078, "贏": 3079, "贼": 3080, "赤": 3081, "赫": 3082, "走": 3083, "赴": 3084, "起": 3085, "趁": 3086, "超": 3087, "越": 3088, "趌": 3089, "趕": 3090, "趙": 3091, "趣": 3092, "趨": 3093, "足": 3094, "趴": 3095, "趺": 3096, "趾": 3097, "跋": 3098, "跌": 3099, "跑": 3100, "跛": 3101, "距": 3102, "跟": 3103, "跡": 3104, "跣": 3105, "跨": 3106, "跪": 3107, "路": 3108, "跳": 3109, "踎": 3110, "踏": 3111, "踐": 3112, "踢": 3113, "踩": 3114, "踪": 3115, "踱": 3116, "踹": 3117, "蹄": 3118, "蹈": 3119, "蹋": 3120, "蹟": 3121, "蹤": 3122, "蹲": 3123, "蹺": 3124, "躁": 3125, "躉": 3126, "躍": 3127, "躝": 3128, "身": 3129, "躬": 3130, "躲": 3131, "車": 3132, "軌": 3133, "軍": 3134, "軒": 3135, "軟": 3136, "較": 3137, "載": 3138, "輊": 3139, "輋": 3140, "輔": 3141, "輕": 3142, "輘": 3143, "輝": 3144, "輟": 3145, "輩": 3146, "輪": 3147, "輯": 3148, "輷": 3149, "輸": 3150, "輻": 3151, "輾": 3152, "轄": 3153, "轆": 3154, "轉": 3155, "轍": 3156, "轡": 3157, "辛": 3158, "辜": 3159, "辣": 3160, "辦": 3161, "辨": 3162, "辭": 3163, "辯": 3164, "辰": 3165, "辱": 3166, "農": 3167, "迂": 3168, "迅": 3169, "迍": 3170, "迎": 3171, "近": 3172, "返": 3173, "迦": 3174, "迪": 3175, "迫": 3176, "述": 3177, "迴": 3178, "迷": 3179, "追": 3180, "迾": 3181, "退": 3182, "送": 3183, "逃": 3184, "逆": 3185, "透": 3186, "逐": 3187, "途": 3188, "逗": 3189, "這": 3190, "通": 3191, "逝": 3192, "逞": 3193, "速": 3194, "造": 3195, "逢": 3196, "連": 3197, "週": 3198, "進": 3199, "逸": 3200, "逹": 3201, "逼": 3202, "逾": 3203, "遂": 3204, "遇": 3205, "遊": 3206, "運": 3207, "遍": 3208, "過": 3209, "遏": 3210, "道": 3211, "達": 3212, "違": 3213, "遙": 3214, "遜": 3215, "遞": 3216, "遠": 3217, "遢": 3218, "遣": 3219, "適": 3220, "遭": 3221, "遮": 3222, "遲": 3223, "遴": 3224, "遵": 3225, "遷": 3226, "選": 3227, "遺": 3228, "避": 3229, "邀": 3230, "還": 3231, "邊": 3232, "邋": 3233, "邏": 3234, "那": 3235, "邦": 3236, "邨": 3237, "邪": 3238, "��": 3239, "邵": 3240, "邸": 3241, "郁": 3242, "郊": 3243, "郎": 3244, "郝": 3245, "部": 3246, "郭": 3247, "郵": 3248, "都": 3249, "鄂": 3250, "鄉": 3251, "鄙": 3252, "鄧": 3253, "鄭": 3254, "鄰": 3255, "酌": 3256, "配": 3257, "酒": 3258, "酥": 3259, "酪": 3260, "酬": 3261, "酮": 3262, "酱": 3263, "酷": 3264, "酸": 3265, "醇": 3266, "醉": 3267, "醋": 3268, "醒": 3269, "醜": 3270, "醫": 3271, "醬": 3272, "醺": 3273, "釀": 3274, "采": 3275, "釋": 3276, "里": 3277, "重": 3278, "野": 3279, "量": 3280, "金": 3281, "釗": 3282, "釘": 3283, "釜": 3284, "針": 3285, "釣": 3286, "釵": 3287, "鈍": 3288, "鈔": 3289, "鈕": 3290, "鈴": 3291, "鉛": 3292, "鉤": 3293, "鉸": 3294, "銀": 3295, "銅": 3296, "銘": 3297, "銳": 3298, "銷": 3299, "鋁": 3300, "鋒": 3301, "鋪": 3302, "鋼": 3303, "錄": 3304, "錐": 3305, "錢": 3306, "錦": 3307, "錫": 3308, "錯": 3309, "錶": 3310, "鍊": 3311, "鍋": 3312, "鍚": 3313, "鍵": 3314, "鍾": 3315, "鎖": 3316, "鎗": 3317, "鎭": 3318, "鎮": 3319, "鏈": 3320, "鏟": 3321, "鏡": 3322, "鏰": 3323, "鐘": 3324, "鐡": 3325, "鐵": 3326, "鐸": 3327, "鑄": 3328, "鑊": 3329, "鑑": 3330, "鑫": 3331, "鑲": 3332, "鑼": 3333, "鑽": 3334, "鑿": 3335, "長": 3336, "門": 3337, "閂": 3338, "閃": 3339, "閉": 3340, "開": 3341, "閏": 3342, "閒": 3343, "間": 3344, "閘": 3345, "閣": 3346, "閨": 3347, "閩": 3348, "閱": 3349, "閻": 3350, "闆": 3351, "闊": 3352, "闌": 3353, "闔": 3354, "闖": 3355, "關": 3356, "闢": 3357, "阜": 3358, "阪": 3359, "阱": 3360, "防": 3361, "阻": 3362, "阿": 3363, "陀": 3364, "陂": 3365, "附": 3366, "陌": 3367, "降": 3368, "限": 3369, "陞": 3370, "院": 3371, "陣": 3372, "除": 3373, "陪": 3374, "陰": 3375, "陳": 3376, "陶": 3377, "陷": 3378, "陸": 3379, "陽": 3380, "隆": 3381, "隊": 3382, "階": 3383, "隔": 3384, "隙": 3385, "際": 3386, "障": 3387, "隧": 3388, "隨": 3389, "險": 3390, "隱": 3391, "隴": 3392, "隸": 3393, "隻": 3394, "雀": 3395, "雁": 3396, "雄": 3397, "雅": 3398, "集": 3399, "雋": 3400, "雌": 3401, "雍": 3402, "雖": 3403, "雙": 3404, "雜": 3405, "雞": 3406, "離": 3407, "難": 3408, "雨": 3409, "雪": 3410, "雲": 3411, "零": 3412, "雷": 3413, "電": 3414, "需": 3415, "霄": 3416, "震": 3417, "霉": 3418, "霎": 3419, "霖": 3420, "霜": 3421, "霧": 3422, "露": 3423, "霸": 3424, "靈": 3425, "青": 3426, "靖": 3427, "靚": 3428, "靜": 3429, "非": 3430, "靠": 3431, "面": 3432, "革": 3433, "靴": 3434, "靶": 3435, "鞋": 3436, "鞍": 3437, "鞦": 3438, "鞭": 3439, "韆": 3440, "韌": 3441, "韓": 3442, "音": 3443, "韻": 3444, "響": 3445, "頁": 3446, "頂": 3447, "項": 3448, "順": 3449, "須": 3450, "頌": 3451, "預": 3452, "頒": 3453, "頓": 3454, "頗": 3455, "領": 3456, "頤": 3457, "頭": 3458, "頸": 3459, "頻": 3460, "題": 3461, "額": 3462, "顏": 3463, "顔": 3464, "願": 3465, "顛": 3466, "類": 3467, "顧": 3468, "顯": 3469, "顱": 3470, "風": 3471, "颱": 3472, "飄": 3473, "飛": 3474, "食": 3475, "飢": 3476, "飯": 3477, "飲": 3478, "飼": 3479, "飽": 3480, "飾": 3481, "餃": 3482, "餅": 3483, "餉": 3484, "養": 3485, "餋": 3486, "餐": 3487, "餒": 3488, "餓": 3489, "餘": 3490, "館": 3491, "餵": 3492, "餸": 3493, "餼": 3494, "饅": 3495, "饌": 3496, "饑": 3497, "饒": 3498, "饕": 3499, "首": 3500, "香": 3501, "馨": 3502, "馬": 3503, "馮": 3504, "馳": 3505, "駁": 3506, "駐": 3507, "駒": 3508, "駕": 3509, "駛": 3510, "駝": 3511, "駟": 3512, "駱": 3513, "駿": 3514, "騅": 3515, "騎": 3516, "騙": 3517, "騭": 3518, "騮": 3519, "騰": 3520, "騷": 3521, "騾": 3522, "驅": 3523, "驕": 3524, "驗": 3525, "驚": 3526, "驟": 3527, "驥": 3528, "骨": 3529, "骹": 3530, "髀": 3531, "髓": 3532, "體": 3533, "高": 3534, "髮": 3535, "髻": 3536, "鬆": 3537, "鬚": 3538, "鬠": 3539, "鬢": 3540, "鬥": 3541, "鬧": 3542, "鬱": 3543, "鬼": 3544, "魁": 3545, "魂": 3546, "魄": 3547, "魅": 3548, "魏": 3549, "魔": 3550, "魚": 3551, "魯": 3552, "魷": 3553, "鮑": 3554, "鮟": 3555, "鮫": 3556, "鮭": 3557, "鮮": 3558, "鯇": 3559, "鯉": 3560, "鯊": 3561, "鯖": 3562, "鯛": 3563, "鯪": 3564, "鰂": 3565, "鰭": 3566, "鰻": 3567, "鱇": 3568, "鱈": 3569, "鱔": 3570, "鱗": 3571, "鱲": 3572, "鱷": 3573, "鱸": 3574, "鲁": 3575, "鳥": 3576, "鳩": 3577, "鳳": 3578, "鳴": 3579, "鳶": 3580, "鴉": 3581, "鴛": 3582, "鴦": 3583, "鴨": 3584, "鴻": 3585, "鴿": 3586, "鵝": 3587, "鵪": 3588, "鵬": 3589, "鵲": 3590, "鶉": 3591, "鶴": 3592, "鷄": 3593, "鷯": 3594, "鷹": 3595, "鸞": 3596, "鹅": 3597, "鹹": 3598, "鹼": 3599, "鹽": 3600, "鹿": 3601, "麒": 3602, "麗": 3603, "麝": 3604, "麟": 3605, "麥": 3606, "麪": 3607, "麵": 3608, "麻": 3609, "麼": 3610, "黃": 3611, "黎": 3612, "黏": 3613, "黐": 3614, "黑": 3615, "默": 3616, "黚": 3617, "黛": 3618, "黜": 3619, "點": 3620, "黨": 3621, "黯": 3622, "鼆": 3623, "鼎": 3624, "鼓": 3625, "鼠": 3626, "鼻": 3627, "齊": 3628, "齋": 3629, "齒": 3630, "齡": 3631, "齪": 3632, "齷": 3633, "龍": 3634, "龐": 3635, "龜": 3636, "龢": 3637, "更": 3638, "來": 3639, "不": 3640, "年": 3641, "聯": 3642, "料": 3643, "利": 3644, "立": 3645, "行": 3646, "．": 3647, "ａ": 3648, "ｂ": 3649, "": 3650, "|": 0, "[UNK]": 3651, "[PAD]": 3652}