End of training

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+base_model: fleek/wav2vec-large-xlsr-korean
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-xlsr-korean-dialect-recognition
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2-xlsr-korean-dialect-recognition
+
+This model is a fine-tuned version of [fleek/wav2vec-large-xlsr-korean](https://huggingface.co/fleek/wav2vec-large-xlsr-korean) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5291
+- Accuracy: 0.8063
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 2.8542        | 0.0681 | 100  | 1.4936          | 0.3803   |
+| 1.9555        | 0.1362 | 200  | 1.1916          | 0.5237   |
+| 2.3132        | 0.2043 | 300  | 0.9826          | 0.6180   |
+| 1.8724        | 0.2724 | 400  | 0.9512          | 0.6411   |
+| 1.9331        | 0.3405 | 500  | 0.8138          | 0.6857   |
+| 1.6761        | 0.4086 | 600  | 0.7749          | 0.6932   |
+| 1.7902        | 0.4767 | 700  | 0.7694          | 0.7028   |
+| 1.9041        | 0.5448 | 800  | 0.7199          | 0.7194   |
+| 1.8659        | 0.6129 | 900  | 0.7010          | 0.7382   |
+| 1.9123        | 0.6810 | 1000 | 0.6067          | 0.7753   |
+| 1.2564        | 0.7491 | 1100 | 0.6073          | 0.7726   |
+| 0.8368        | 0.8172 | 1200 | 0.6203          | 0.7729   |
+| 1.1841        | 0.8853 | 1300 | 0.5312          | 0.7988   |
+| 1.0372        | 0.9534 | 1400 | 0.5291          | 0.8063   |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,135 @@
+{
+  "_name_or_path": "fleek/wav2vec-large-xlsr-korean",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSpeechClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "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,
+  "finetuning_task": "wav2vec2_clf",
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Gyeongsang-do",
+    "1": "Jeolla-do",
+    "2": "Chungcheong-do",
+    "3": "Jeju-do",
+    "4": "Gangwon-do",
+    "5": "Seoul/Gyeonggi-do"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Chungcheong-do": 2,
+    "Gangwon-do": 4,
+    "Gyeongsang-do": 0,
+    "Jeju-do": 3,
+    "Jeolla-do": 1,
+    "Seoul/Gyeonggi-do": 5
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 49,
+  "pooling_mode": "mean",
+  "problem_type": "single_label_classification",
+  "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
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 50,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7269f0b6ef8e3e2ab79c6e52e1dfe4efbfee9e9120e9c16caeb52150b16d5edd
+size 1266030704

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

tokenizer.config

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": true, "word_delimiter_token": "|", "tokenizer_file": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7745b44a5432474fb1608d076a2864a64b11824ab3e38cb012c791535cc99405
+size 5368