metadata
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-base-finetune-vi-v5
results: []
wav2vec2-base-finetune-vi-v5
This model is a fine-tuned version of foxxy-hm/wav2vec2-base-finetune-vi-v5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2484
- Wer: 0.1527
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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 11.2332 | 0.49 | 500 | 3.4000 | 1.0 |
| 1.4014 | 0.99 | 1000 | 0.3058 | 0.1825 |
| 0.1614 | 1.48 | 1500 | 0.2742 | 0.1646 |
| 0.1269 | 1.98 | 2000 | 0.2791 | 0.1628 |
| 0.0991 | 2.47 | 2500 | 0.2642 | 0.1589 |
| 0.0913 | 2.96 | 3000 | 0.2483 | 0.1555 |
| 0.0833 | 3.46 | 3500 | 0.2528 | 0.1535 |
| 0.0787 | 3.95 | 4000 | 0.2484 | 0.1527 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.8.0
- Tokenizers 0.13.3