Whisper Tiny Viet - Chee Li
This model is a fine-tuned version of openai/whisper-tiny on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.9492
- Wer: 113.9086
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2593 | 4.7619 | 1000 | 0.7965 | 83.3513 |
| 0.0633 | 9.5238 | 2000 | 0.8520 | 143.8831 |
| 0.0165 | 14.2857 | 3000 | 0.9207 | 117.2121 |
| 0.0111 | 19.0476 | 4000 | 0.9492 | 113.9086 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for CheeLi03/whisper-tiny-vi-puct-4k
Base model
openai/whisper-tiny