Whisper Small Zulu
This model is a fine-tuned version of openai/whisper-small on the google/fleurs zu_za dataset. It achieves the following results on the evaluation set:
- Loss: 1.1143
- Wer: 56.7866
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.6219 | 9.01 | 100 | 1.0758 | 62.0201 |
| 0.0318 | 18.01 | 200 | 1.1143 | 56.7866 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Dataset used to train arun100/whisper-small-zu_za
Evaluation results
- Wer on google/fleurs zu_zatest set self-reported56.787