whisper-small-dora-afrispeech-general
This model is a fine-tuned version of openai/whisper-small on the afrispeech-200 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5790
- Wer: 0.174
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1349
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5423 | 1.0 | 1350 | 0.6201 | 0.192 |
| 0.4544 | 2.0 | 2700 | 0.5490 | 0.175 |
| 0.3377 | 3.0 | 4050 | 0.5355 | 0.164 |
| 0.2578 | 4.0 | 5400 | 0.5424 | 0.168 |
| 0.1971 | 5.0 | 6750 | 0.5624 | 0.168 |
| 0.1509 | 6.0 | 8100 | 0.5790 | 0.174 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.10.0+cu128
- Datasets 2.19.0
- Tokenizers 0.19.1