WhisperYoruba
This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0256
- Wer: 51.0719
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2736 | 3.8462 | 1000 | 0.7361 | 51.3661 |
| 0.0192 | 7.6923 | 2000 | 0.9077 | 51.7697 |
| 0.0013 | 11.5385 | 3000 | 1.0256 | 51.0719 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 3.2.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for EYEDOL/Yoruba-ASR
Base model
openai/whisper-small