metadata
library_name: transformers
language:
- vi
license: bsd-3-clause
base_model: vinai/PhoWhisper-base
tags:
- generated_from_trainer
datasets:
- nguyendv02/ViMD_Dataset
metrics:
- wer
model-index:
- name: Pho Whisper Base - ViMD
results: []
Pho Whisper Base - ViMD
This model is a fine-tuned version of vinai/PhoWhisper-base on the ViMD dataset. It achieves the following results on the evaluation set:
- Loss: 0.3062
- Wer: 19.3867
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2943 | 1.0650 | 1000 | 0.3295 | 20.7727 |
| 0.2157 | 2.1299 | 2000 | 0.3062 | 19.3097 |
| 0.1877 | 3.1949 | 3000 | 0.3052 | 19.4259 |
| 0.1673 | 4.2599 | 4000 | 0.3062 | 19.3867 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.0
- Tokenizers 0.21.0