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: 0.3391
- Wer: 30.7136
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 |
|---|---|---|---|---|
| 0.1672 | 0.0998 | 500 | 0.3706 | 33.9074 |
| 0.172 | 0.1996 | 1000 | 0.3714 | 33.9803 |
| 0.2094 | 0.2995 | 1500 | 0.3640 | 33.2407 |
| 0.1927 | 0.3993 | 2000 | 0.3577 | 32.5233 |
| 0.1905 | 0.4991 | 2500 | 0.3521 | 31.8810 |
| 0.1735 | 0.5989 | 3000 | 0.3470 | 31.3189 |
| 0.157 | 0.6987 | 3500 | 0.3428 | 31.0052 |
| 0.1784 | 0.7986 | 4000 | 0.3391 | 30.7136 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 3