metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-finetuned-amharic
results: []
whisper-finetuned-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: 1.5902
- Wer: 2.7316
- Cer: 3.0021
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: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 2.0672 | 0.1 | 20 | 1.9614 | 1.0866 | 2.5477 |
| 1.8145 | 0.2 | 40 | 1.8406 | 1.0157 | 2.5646 |
| 1.8231 | 0.3 | 60 | 1.7589 | 2.3898 | 2.7175 |
| 1.7399 | 0.4 | 80 | 1.7080 | 2.2848 | 2.6377 |
| 1.6576 | 0.5 | 100 | 1.6876 | 1.8097 | 2.5961 |
| 1.6655 | 0.6 | 120 | 1.6609 | 3.3871 | 3.1712 |
| 1.6613 | 0.7 | 140 | 1.6364 | 2.8038 | 3.0409 |
| 1.6039 | 0.8 | 160 | 1.6145 | 1.25 | 2.6169 |
| 1.5773 | 0.9 | 180 | 1.6039 | 1.2421 | 2.6039 |
| 1.5844 | 1.0 | 200 | 1.5902 | 2.7316 | 3.0021 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0