whisper_amharic
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6776
- Wer: 3.06
- Cer: 3.1294
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: 2
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 2.2053 | 0.5 | 20 | 1.9974 | 4.5933 | 3.3748 |
| 1.8705 | 1.0 | 40 | 1.8153 | 3.2333 | 3.0812 |
| 1.7553 | 1.5 | 60 | 1.7752 | 1.7267 | 2.8164 |
| 1.7049 | 2.0 | 80 | 1.7236 | 3.4533 | 3.1455 |
| 1.6274 | 2.5 | 100 | 1.6928 | 2.5267 | 2.9721 |
| 1.5948 | 3.0 | 120 | 1.6776 | 3.06 | 3.1294 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 34
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 Bedru/whisper_amharic
Base model
openai/whisper-small