whisper-small-yue-fold-3
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2815
- Wer: 83.6735
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: 32
- eval_batch_size: 16
- 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: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.7804 | 0.38 | 50 | 2.2963 | 123.7477 |
| 0.7908 | 0.75 | 100 | 0.4247 | 199.6289 |
| 0.305 | 1.13 | 150 | 0.3275 | 124.2115 |
| 0.2708 | 1.5 | 200 | 0.2999 | 104.6382 |
| 0.2586 | 1.88 | 250 | 0.2925 | 74.5826 |
| 0.1571 | 2.26 | 300 | 0.2853 | 78.6642 |
| 0.1575 | 2.63 | 350 | 0.2780 | 75.0464 |
| 0.1431 | 3.01 | 400 | 0.2815 | 83.6735 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 1.12.1
- Datasets 2.15.0
- Tokenizers 0.15.0