Whisper Small zh-TW
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2271
- Wer: 40.4120
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 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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0964 | 1.4184 | 1000 | 0.1998 | 41.1552 |
| 0.0317 | 2.8369 | 2000 | 0.2073 | 41.5375 |
| 0.0049 | 4.2553 | 3000 | 0.2142 | 40.4757 |
| 0.0015 | 5.6738 | 4000 | 0.2238 | 40.5606 |
| 0.0009 | 7.0922 | 5000 | 0.2271 | 40.4120 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 76
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for B20662/whisper-small-zh-TW
Base model
openai/whisper-small