<!-- 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. -->
whisper-vietnamese
This model is a fine-tuned version of duytran3112/whisper-sm-vivos on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5021
- Wer: 143.3132
- Cer: 170.7314
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.1927 | 3.07 | 1000 | 0.4454 | 99.8576 | 86.3335 |
| 0.0144 | 6.13 | 2000 | 0.4553 | 190.2670 | 169.4322 |
| 0.0029 | 9.2 | 3000 | 0.4889 | 144.1729 | 165.2591 |
| 0.0018 | 12.27 | 4000 | 0.5021 | 143.3132 | 170.7314 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.0
- Datasets 2.14.4
- Tokenizers 0.13.3
