Upload 12 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 44,
+  "[PAD]": 43
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "team-lucid/hubert-base-korean",
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.05,
+  "auto_map": {
+    "FlaxAutoModel": "team-lucid/hubert-base-korean--modeling_flax_hubert.FlaxHubertModel"
+  },
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.05,
+  "feat_proj_layer_norm": true,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "final_proj_size": 256,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 43,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 44,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442890236a18c917054441b22505ea4ec72b244489707dac3fb027bb259f40f0
+size 377648040

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74985c6d6e067933c87425cb03e0748930ac4562d3a9dc6a5644e0246f4e148e
+size 60152540

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "cache_dir": "/content/drive/MyDrive/forcashe2",
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a49161e423813b24182d8eb330a853e30fed5abb1f1538e1937b05fff0231a
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a9c99832057a33608534462faba765d704b65f0aa8ebb8f7abcc1df83206d5
+size 1064

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "42": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "cache_dir": "/content/drive/MyDrive/forcashe2",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

trainer_state.json

@@ -0,0 +1,222 @@
+{
+  "best_metric": 0.1455519050359726,
+  "best_model_checkpoint": "for_test25/checkpoint-2000",
+  "epoch": 4.7281323877068555,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2364066193853428,
+      "grad_norm": 60.020355224609375,
+      "learning_rate": 2.4e-05,
+      "loss": 9.8742,
+      "step": 100
+    },
+    {
+      "epoch": 0.4728132387706856,
+      "grad_norm": 4.358085632324219,
+      "learning_rate": 4.9e-05,
+      "loss": 4.8037,
+      "step": 200
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 10.840340614318848,
+      "learning_rate": 7.4e-05,
+      "loss": 4.1932,
+      "step": 300
+    },
+    {
+      "epoch": 0.9456264775413712,
+      "grad_norm": 22.108749389648438,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 3.9676,
+      "step": 400
+    },
+    {
+      "epoch": 1.1820330969267139,
+      "grad_norm": 12.02284049987793,
+      "learning_rate": 9.74934725848564e-05,
+      "loss": 3.8466,
+      "step": 500
+    },
+    {
+      "epoch": 1.1820330969267139,
+      "eval_PER": 0.9633641181124875,
+      "eval_loss": 4.664893627166748,
+      "eval_runtime": 420.6139,
+      "eval_samples_per_second": 11.84,
+      "eval_steps_per_second": 0.742,
+      "learning_rate": 9.74934725848564e-05,
+      "step": 500
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 10.632979393005371,
+      "learning_rate": 9.488250652741515e-05,
+      "loss": 3.6831,
+      "step": 600
+    },
+    {
+      "epoch": 1.6548463356973995,
+      "grad_norm": 3.2810802459716797,
+      "learning_rate": 9.22715404699739e-05,
+      "loss": 3.7744,
+      "step": 700
+    },
+    {
+      "epoch": 1.8912529550827424,
+      "grad_norm": 1.6217520236968994,
+      "learning_rate": 8.966057441253264e-05,
+      "loss": 3.4184,
+      "step": 800
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 12.222310066223145,
+      "learning_rate": 8.704960835509139e-05,
+      "loss": 3.7714,
+      "step": 900
+    },
+    {
+      "epoch": 2.3640661938534278,
+      "grad_norm": 6.44509220123291,
+      "learning_rate": 8.443864229765015e-05,
+      "loss": 3.4804,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3640661938534278,
+      "eval_PER": 0.9612962852146624,
+      "eval_loss": 3.0293383598327637,
+      "eval_runtime": 424.1378,
+      "eval_samples_per_second": 11.741,
+      "eval_steps_per_second": 0.736,
+      "learning_rate": 8.443864229765015e-05,
+      "step": 1000
+    },
+    {
+      "epoch": 2.6004728132387704,
+      "grad_norm": 8.923386573791504,
+      "learning_rate": 8.182767624020888e-05,
+      "loss": 3.3555,
+      "step": 1100
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "grad_norm": 0.9465563297271729,
+      "learning_rate": 7.921671018276762e-05,
+      "loss": 2.2104,
+      "step": 1200
+    },
+    {
+      "epoch": 3.0732860520094563,
+      "grad_norm": 0.8739014863967896,
+      "learning_rate": 7.660574412532637e-05,
+      "loss": 1.4531,
+      "step": 1300
+    },
+    {
+      "epoch": 3.309692671394799,
+      "grad_norm": 0.7739846110343933,
+      "learning_rate": 7.399477806788511e-05,
+      "loss": 1.4319,
+      "step": 1400
+    },
+    {
+      "epoch": 3.546099290780142,
+      "grad_norm": 3.5161337852478027,
+      "learning_rate": 7.138381201044386e-05,
+      "loss": 1.2535,
+      "step": 1500
+    },
+    {
+      "epoch": 3.546099290780142,
+      "eval_PER": 0.10295114994115652,
+      "eval_loss": 0.18029829859733582,
+      "eval_runtime": 420.7727,
+      "eval_samples_per_second": 11.835,
+      "eval_steps_per_second": 0.741,
+      "learning_rate": 7.138381201044386e-05,
+      "step": 1500
+    },
+    {
+      "epoch": 3.7825059101654848,
+      "grad_norm": 2.1900475025177,
+      "learning_rate": 6.877284595300262e-05,
+      "loss": 1.1847,
+      "step": 1600
+    },
+    {
+      "epoch": 4.0189125295508275,
+      "grad_norm": 1.6488945484161377,
+      "learning_rate": 6.616187989556137e-05,
+      "loss": 1.166,
+      "step": 1700
+    },
+    {
+      "epoch": 4.25531914893617,
+      "grad_norm": 1.0157734155654907,
+      "learning_rate": 6.355091383812011e-05,
+      "loss": 1.6181,
+      "step": 1800
+    },
+    {
+      "epoch": 4.491725768321513,
+      "grad_norm": 0.4091039299964905,
+      "learning_rate": 6.093994778067885e-05,
+      "loss": 1.4641,
+      "step": 1900
+    },
+    {
+      "epoch": 4.7281323877068555,
+      "grad_norm": 0.38830655813217163,
+      "learning_rate": 5.8328981723237596e-05,
+      "loss": 1.304,
+      "step": 2000
+    },
+    {
+      "epoch": 4.7281323877068555,
+      "eval_PER": 0.09349463759732445,
+      "eval_loss": 0.1455519050359726,
+      "eval_runtime": 417.7255,
+      "eval_samples_per_second": 11.922,
+      "eval_steps_per_second": 0.747,
+      "learning_rate": 5.8328981723237596e-05,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4230,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1795037641339611e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd517f629f9df66eb7771fe5638a6ee6f3f0ec471543c136a4e41d6f3f90ca7
+size 5240

vocab.json

@@ -0,0 +1,45 @@
+{
+  "[PAD]": 43,
+  "[UNK]": 42,
+  "|": 41,
+  "ㄱ": 1,
+  "ㄲ": 2,
+  "ㄴ": 3,
+  "ㄷ": 4,
+  "ㄸ": 5,
+  "ㄹ": 6,
+  "ㅁ": 7,
+  "ㅂ": 8,
+  "ㅃ": 9,
+  "ㅅ": 10,
+  "ㅆ": 11,
+  "ㅇ": 12,
+  "ㅈ": 13,
+  "ㅉ": 14,
+  "ㅊ": 15,
+  "ㅋ": 16,
+  "ㅌ": 17,
+  "ㅍ": 18,
+  "ㅎ": 19,
+  "ㅏ": 20,
+  "ㅐ": 21,
+  "ㅑ": 22,
+  "ㅒ": 23,
+  "ㅓ": 24,
+  "ㅔ": 25,
+  "ㅕ": 26,
+  "ㅖ": 27,
+  "ㅗ": 28,
+  "ㅘ": 29,
+  "ㅙ": 30,
+  "ㅚ": 31,
+  "ㅛ": 32,
+  "ㅜ": 33,
+  "ㅝ": 34,
+  "ㅞ": 35,
+  "ㅟ": 36,
+  "ㅠ": 37,
+  "ㅡ": 38,
+  "ㅢ": 39,
+  "ㅣ": 40
+}