Whisper Small CN - my voice with CER metric
This model is a fine-tuned version of openai/whisper-small on the my_CN_ds dataset. It achieves the following results on the evaluation set:
- Loss: 0.7618
- Cer: 44.3038
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: 50
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0001 | 100.0 | 100 | 0.7589 | 35.4430 |
| 0.0 | 200.0 | 200 | 0.7597 | 44.3038 |
| 0.0 | 300.0 | 300 | 0.7608 | 44.3038 |
| 0.0 | 400.0 | 400 | 0.7618 | 44.3038 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1