jinkrsmodel
This model is a fine-tuned version of openai/whisper-medium on the DianaJin/logi dataset. It achieves the following results on the evaluation set:
- Loss: 3.2265
- Cer: 100.0
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: 250
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0004 | 250.0 | 500 | 2.3248 | 100.0 |
| 0.0002 | 500.0 | 1000 | 2.3827 | 100.0 |
| 0.0002 | 750.0 | 1500 | 2.9600 | 100.0 |
| 0.0002 | 1000.0 | 2000 | 3.2265 | 100.0 |
Framework versions
- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 7