|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: nguyenvulebinh/wav2vec2-base-vi |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2_base_vietnamese_control_dataset_75_epochs |
|
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_base_vietnamese_control_dataset_75_epochs |
|
|
|
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vi](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0584 |
|
- Wer: 0.1728 |
|
|
|
## 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: 3e-05 |
|
- 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: 75 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 16.8485 | 3.85 | 500 | 15.0708 | 1.0 | |
|
| 7.7941 | 7.69 | 1000 | 5.1283 | 1.0 | |
|
| 3.4391 | 11.54 | 1500 | 3.2167 | 1.0 | |
|
| 3.116 | 15.38 | 2000 | 3.1172 | 1.0 | |
|
| 3.0946 | 19.23 | 2500 | 3.1165 | 1.0 | |
|
| 3.0478 | 23.08 | 3000 | 2.9426 | 1.0 | |
|
| 2.4567 | 26.92 | 3500 | 1.6121 | 0.9993 | |
|
| 1.2305 | 30.77 | 4000 | 0.5487 | 0.3630 | |
|
| 0.5512 | 34.62 | 4500 | 0.2505 | 0.2364 | |
|
| 0.3234 | 38.46 | 5000 | 0.1572 | 0.1869 | |
|
| 0.2232 | 42.31 | 5500 | 0.1170 | 0.1782 | |
|
| 0.1779 | 46.15 | 6000 | 0.0939 | 0.1772 | |
|
| 0.145 | 50.0 | 6500 | 0.0830 | 0.1763 | |
|
| 0.1383 | 53.85 | 7000 | 0.0739 | 0.1756 | |
|
| 0.1161 | 57.69 | 7500 | 0.0681 | 0.1736 | |
|
| 0.1054 | 61.54 | 8000 | 0.0630 | 0.1729 | |
|
| 0.0958 | 65.38 | 8500 | 0.0620 | 0.1729 | |
|
| 0.1028 | 69.23 | 9000 | 0.0582 | 0.1726 | |
|
| 0.1015 | 73.08 | 9500 | 0.0584 | 0.1728 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
