metadata
license: cc-by-nc-4.0
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
base_model: nguyenvulebinh/wav2vec2-base-vietnamese-250h
model-index:
- name: result_weight
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: vi
split: None
args: vi
metrics:
- type: wer
value: 0.7862032648762507
name: Wer
result_weight
This model is a fine-tuned version of nguyenvulebinh/wav2vec2-base-vietnamese-250h on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6430
- Wer: 0.7862
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 |
|---|---|---|---|---|
| 19.1789 | 6.3291 | 500 | 5.0724 | 1.0 |
| 4.4582 | 12.6582 | 1000 | 3.4558 | 0.9989 |
| 3.8596 | 18.9873 | 1500 | 3.1687 | 0.9905 |
| 2.8095 | 25.3165 | 2000 | 2.2626 | 0.9084 |
| 2.0404 | 31.6456 | 2500 | 1.8938 | 0.8220 |
| 1.6879 | 37.9747 | 3000 | 1.6430 | 0.7862 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1