Whisper base acholi
This model is a fine-tuned version of openai/whisper-small on the Sunbird dataset. It achieves the following results on the evaluation set:
- Loss: 2.8895
- Wer: 122.2638
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.2321 | 3.32 | 1000 | 2.9610 | 140.3181 |
| 2.5056 | 6.64 | 2000 | 2.7358 | 116.9317 |
| 2.0671 | 9.97 | 3000 | 2.7957 | 144.9953 |
| 1.7382 | 13.29 | 4000 | 2.8895 | 122.2638 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 0