---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
model-index:
- name: v7-fine-tune-wav2vec2-Vietnamese-ARS-demo
  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. -->

# v7-fine-tune-wav2vec2-Vietnamese-ARS-demo

This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2806
- Wer: 0.2751

## 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: 8
- 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: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer    |
|:-------------:|:-----:|:-----:|:---------------:|:------:|
| 10.9724       | 0.34  | 500   | 3.8863          | 1.0    |
| 3.4322        | 0.69  | 1000  | 2.6994          | 1.0953 |
| 2.431         | 1.03  | 1500  | 1.6603          | 1.0447 |
| 1.6436        | 1.37  | 2000  | 0.8842          | 0.7589 |
| 1.1161        | 1.71  | 2500  | 0.6005          | 0.5565 |
| 0.8657        | 2.06  | 3000  | 0.4911          | 0.4680 |
| 0.7653        | 2.4   | 3500  | 0.4501          | 0.4207 |
| 0.7013        | 2.74  | 4000  | 0.4149          | 0.3994 |
| 0.6306        | 3.09  | 4500  | 0.4065          | 0.3761 |
| 0.602         | 3.43  | 5000  | 0.3846          | 0.3682 |
| 0.5746        | 3.77  | 5500  | 0.3814          | 0.3486 |
| 0.5199        | 4.12  | 6000  | 0.3753          | 0.3354 |
| 0.4901        | 4.46  | 6500  | 0.3437          | 0.3228 |
| 0.4834        | 4.8   | 7000  | 0.3329          | 0.3175 |
| 0.4553        | 5.14  | 7500  | 0.3257          | 0.3135 |
| 0.4501        | 5.49  | 8000  | 0.3156          | 0.3077 |
| 0.4468        | 5.83  | 8500  | 0.3248          | 0.3072 |
| 0.4078        | 6.17  | 9000  | 0.3174          | 0.3033 |
| 0.4215        | 6.52  | 9500  | 0.3064          | 0.2959 |
| 0.4001        | 6.86  | 10000 | 0.3158          | 0.2936 |
| 0.3983        | 7.2   | 10500 | 0.3022          | 0.2890 |
| 0.3955        | 7.54  | 11000 | 0.2938          | 0.2890 |
| 0.381         | 7.89  | 11500 | 0.2893          | 0.2915 |
| 0.3484        | 8.23  | 12000 | 0.2881          | 0.2835 |
| 0.3492        | 8.57  | 12500 | 0.2899          | 0.2809 |
| 0.3825        | 8.92  | 13000 | 0.2857          | 0.2808 |
| 0.3356        | 9.26  | 13500 | 0.2841          | 0.2789 |
| 0.3361        | 9.6   | 14000 | 0.2789          | 0.2753 |
| 0.3353        | 9.95  | 14500 | 0.2806          | 0.2751 |


### Framework versions

- Transformers 4.17.0
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.12.1