Wisper-Small-zh-TW
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2293
- Cer: 10.0703
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 | Cer |
|---|---|---|---|---|
| 0.106 | 1.3245 | 1000 | 0.2137 | 10.6904 |
| 0.0321 | 2.6490 | 2000 | 0.2127 | 10.5172 |
| 0.0093 | 3.9735 | 3000 | 0.2222 | 10.1029 |
| 0.0021 | 5.2980 | 4000 | 0.2293 | 10.0703 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 36
Unable to determine this model’s pipeline type. Check the
docs
.