metadata
license: apache-2.0
base_model: Thienpkae/wav2vec2-large-xls-r-vi-colab
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-vi-colab
results: []
wav2vec2-large-xls-r-vi-colab
This model is a fine-tuned version of Thienpkae/wav2vec2-large-xls-r-vi-colab on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8989
- Wer: 0.9376
- Cer: 0.3861
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: 330
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.533 | 7.5 | 165 | 3.3635 | 1.0 | 1.0 |
| 3.5135 | 15.0 | 330 | 3.3336 | 1.0 | 1.0 |
| 3.6414 | 22.5 | 495 | 3.0578 | 0.9995 | 0.8722 |
| 2.1098 | 30.0 | 660 | 1.8989 | 0.9376 | 0.3861 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1