Whisper Small Chinese
This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 zh-CN dataset. It achieves the following results on the evaluation set:
- Loss: 0.3813
- Cer: 15.3563
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.481 | 1.07 | 1000 | 0.3443 | 16.1736 |
| 0.2912 | 3.0 | 2000 | 0.3487 | 16.5213 |
| 0.1303 | 4.07 | 3000 | 0.3707 | 15.3950 |
| 0.0997 | 6.01 | 4000 | 0.3813 | 15.3563 |
| 0.0388 | 7.07 | 5000 | 0.3882 | 15.5099 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.11.1.dev0
- Tokenizers 0.13.2