End of training

README.md

@@ -0,0 +1,104 @@
+---
+license: cc-by-nc-4.0
+base_model: nguyenvulebinh/wav2vec2-base-vietnamese-250h
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: model_weight
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: vi
+      split: None
+      args: vi
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.14013683555810727
+---
+
+<!-- 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. -->
+
+# model_weight
+
+This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1765
+- Wer: 0.1401
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 40
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Wer    |
+|:-------------:|:-------:|:-----:|:---------------:|:------:|
+| 15.0719       | 1.3928  | 500   | 4.8260          | 1.0    |
+| 4.4273        | 2.7855  | 1000  | 4.6865          | 0.9991 |
+| 3.9296        | 4.1783  | 1500  | 4.2965          | 0.9992 |
+| 3.4964        | 5.5710  | 2000  | 2.6642          | 0.9583 |
+| 2.8184        | 6.9638  | 2500  | 1.7146          | 0.8718 |
+| 2.132         | 8.3565  | 3000  | 1.4549          | 0.7103 |
+| 1.7481        | 9.7493  | 3500  | 0.9072          | 0.5730 |
+| 1.5776        | 11.1421 | 4000  | 0.7414          | 0.5132 |
+| 1.3743        | 12.5348 | 4500  | 0.6621          | 0.4089 |
+| 1.2417        | 13.9276 | 5000  | 0.4884          | 0.3854 |
+| 1.1375        | 15.3203 | 5500  | 0.3561          | 0.3123 |
+| 1.0412        | 16.7131 | 6000  | 0.3344          | 0.2945 |
+| 0.981         | 18.1058 | 6500  | 0.3063          | 0.2667 |
+| 0.9913        | 19.4986 | 7000  | 0.2778          | 0.2244 |
+| 0.861         | 20.8914 | 7500  | 0.2511          | 0.2170 |
+| 0.8314        | 22.2841 | 8000  | 0.2498          | 0.2127 |
+| 0.8669        | 23.6769 | 8500  | 0.2452          | 0.2048 |
+| 0.8003        | 25.0696 | 9000  | 0.2251          | 0.1830 |
+| 0.7409        | 26.4624 | 9500  | 0.2292          | 0.1820 |
+| 0.7282        | 27.8552 | 10000 | 0.2130          | 0.1681 |
+| 0.7675        | 29.2479 | 10500 | 0.2290          | 0.1796 |
+| 0.7295        | 30.6407 | 11000 | 0.1971          | 0.1617 |
+| 0.6308        | 32.0334 | 11500 | 0.2032          | 0.1555 |
+| 0.6251        | 33.4262 | 12000 | 0.1905          | 0.1515 |
+| 0.5887        | 34.8189 | 12500 | 0.1844          | 0.1481 |
+| 0.6642        | 36.2117 | 13000 | 0.1796          | 0.1444 |
+| 0.6068        | 37.6045 | 13500 | 0.1808          | 0.1417 |
+| 0.5862        | 38.9972 | 14000 | 0.1765          | 0.1401 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "nguyenvulebinh/wav2vec2-base-vietnamese-250h",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "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": "mean",
+  "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,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "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": 95,
+  "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": "4.40.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 110,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88d2b510ae3734c710fefdd7f7796ec853dc950edb759b8eb7f1e8cdc3fd079
+size 377851056

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
+}

runs/Apr29_18-41-35_ef4a9b7669bb/events.out.tfevents.1714416362.ef4a9b7669bb.1107.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7656510bded88e1e1605b64541d6cad1ea0f57ba372a7f0a511bc47a5ffd1fdc
+size 21396

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afbfd9ebfe9041f1c22a72fe5fd73fcde73298728f6ab0cd9c65ffd9de8431ff
+size 5048