in_car_commands_26_mdl__tiny_ver1
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.9884
- Cer: 46.4516
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: 3.75e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| No log | 1.0 | 1 | 5.0038 | 45.1613 |
| No log | 2.0 | 2 | 5.0038 | 46.4516 |
| No log | 3.0 | 3 | 5.0038 | 46.4516 |
| No log | 4.0 | 4 | 5.0038 | 46.4516 |
| No log | 5.0 | 5 | 5.0038 | 46.4516 |
| No log | 6.0 | 6 | 5.0038 | 46.4516 |
| No log | 7.0 | 7 | 5.0045 | 46.4516 |
| No log | 8.0 | 8 | 5.0021 | 46.4516 |
| No log | 9.0 | 9 | 4.9989 | 46.4516 |
| No log | 10.0 | 10 | 4.9884 | 46.4516 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 3
Model tree for Angeriod/in_car_commands_26_mdl__tiny_ver1
Base model
openai/whisper-tiny