Incremental Swahili Luganda
This model is a fine-tuned version of openai/whisper-small on the Mix data dataset. It achieves the following results on the evaluation set:
- Loss: 0.3560
- Wer: 33.5492
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2725 | 0.0810 | 500 | 0.4085 | 38.8803 |
| 0.2921 | 0.1620 | 1000 | 0.4086 | 37.8608 |
| 0.2746 | 0.2431 | 1500 | 0.3969 | 37.2596 |
| 0.2761 | 0.3241 | 2000 | 0.3825 | 36.0743 |
| 0.2799 | 0.4051 | 2500 | 0.3743 | 35.2544 |
| 0.2426 | 0.4861 | 3000 | 0.3672 | 34.4208 |
| 0.267 | 0.5671 | 3500 | 0.3589 | 33.7573 |
| 0.276 | 0.6481 | 4000 | 0.3560 | 33.5492 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 2