whisper-small-l2-arctic-mdd
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2566
- Per: 0.1270
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Per | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 4.0160 | 1.0 | 281 | 0.8301 | 0.2877 | 1.0 | 1.0 | 1.0 |
| 1.8723 | 2.0 | 562 | 0.4383 | 0.1935 | 1.0 | 1.0 | 1.0 |
| 1.3767 | 3.0 | 843 | 0.3416 | 0.1548 | 1.0 | 1.0 | 1.0 |
| 0.9900 | 4.0 | 1124 | 0.2805 | 0.1380 | 1.0 | 1.0 | 1.0 |
| 0.6225 | 5.0 | 1405 | 0.2566 | 0.1270 | 1.0 | 1.0 | 1.0 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2