End of training

README.md

@@ -0,0 +1,86 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: nguyenvulebinh/wav2vec2-base-vi
+tags:
+- generated_from_trainer
+datasets:
+- doof-ferb/LSVSC
+metrics:
+- f1
+model-index:
+- name: vietnamese-regional-accent-classification-model
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: LSVSC
+      type: doof-ferb/LSVSC
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.8217287598030195
+---
+
+<!-- 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. -->
+
+# vietnamese-regional-accent-classification-model
+
+This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on the LSVSC dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5951
+- F1: 0.8217
+
+## 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 11
+
+### Training results
+
+| Training Loss | Epoch | Step | F1     | Validation Loss |
+|:-------------:|:-----:|:----:|:------:|:---------------:|
+| 1.0507        | 1.0   | 44   | 0.7563 | 0.8615          |
+| 0.8157        | 2.0   | 88   | 0.7804 | 0.7120          |
+| 0.7555        | 3.0   | 132  | 0.7981 | 0.6501          |
+| 0.7006        | 4.0   | 176  | 0.7635 | 0.6767          |
+| 0.6825        | 5.0   | 220  | 0.8005 | 0.6370          |
+| 0.6595        | 6.0   | 264  | 0.7735 | 0.6832          |
+| 0.6634        | 7.0   | 308  | 0.8078 | 0.6044          |
+| 0.627         | 8.0   | 352  | 0.7873 | 0.6399          |
+| 0.603         | 9.0   | 396  | 0.8255 | 0.5825          |
+| 0.5977        | 10.0  | 440  | 0.8180 | 0.5931          |
+| 0.5635        | 11.0  | 484  | 0.5951 | 0.8217          |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,120 @@
+{
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vi",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "southern dialect",
+    "1": "northern dialect",
+    "2": "central dialect"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "central dialect": 2,
+    "northern dialect": 1,
+    "southern dialect": 0
+  },
+  "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": 0,
+  "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": "4.45.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 96,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35dbde6f204a411fc70f2875fbca738309b9a8e040388b394b8c98a2f3324f3
+size 378303396

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcaf29e1b16a7ed0c7a617ae03c2dabe6ad14dd4503481cd6e142dfd6be31571
+size 5176