Whisper Small Yoruba - Dere Abdulhameed
This model is a fine-tuned version of DereAbdulhameed/new_whisper_yoruba on the Common Voice 16.1 & SLR86 dataset. It achieves the following results on the evaluation set:
- Loss: 1.7726
- Wer: 33.0814
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: 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0001 | 17.01 | 1000 | 1.6166 | 33.3043 |
| 0.0001 | 35.01 | 2000 | 1.7029 | 32.9563 |
| 0.0 | 53.01 | 3000 | 1.7515 | 33.0868 |
| 0.0 | 71.01 | 4000 | 1.7726 | 33.0814 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7
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.
Model tree for DereAbdulhameed/Whisper-Yoruba
Unable to build the model tree, the base model loops to the model itself. Learn more.