jinkrsmodel
This model is a fine-tuned version of openai/whisper-medium on the DianaJin/show dataset. It achieves the following results on the evaluation set:
- Loss: 1.4034
- Cer: 71.5618
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 |
|---|---|---|---|---|
| 0.0009 | 33.33 | 100 | 1.3346 | 48.9510 |
| 0.0005 | 66.67 | 200 | 1.2890 | 62.7040 |
| 0.0004 | 100.0 | 300 | 1.3687 | 71.0956 |
| 0.0004 | 133.33 | 400 | 1.4034 | 71.5618 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 6