bex_md
This model is a fine-tuned version of openai/whisper-base on the bex_ds dataset. It achieves the following results on the evaluation set:
- Loss: 2.8168
- Cer: 89.6513
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: 0.01
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.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: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.924 | 6.25 | 1000 | 2.8168 | 89.6513 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.0
- Datasets 3.0.2
- Tokenizers 0.20.1
- Downloads last month
- 90
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for hyk000/bokji_ex
Base model
openai/whisper-base