Whisper Small Esperanto v0.2
This model is a fine-tuned version of openai/whisper-small on the Common Voice Scripted Speech 25.0 (Esperanto) dataset. It achieves the following results on the evaluation set:
- Loss: 0.2158
- Wer: 13.9593
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
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.8758 | 0.2143 | 300 | 0.3193 | 20.9223 |
| 3.5591 | 0.4285 | 600 | 0.2574 | 17.7927 |
| 4.3353 | 0.6428 | 900 | 0.2311 | 15.1391 |
| 4.0004 | 0.8570 | 1200 | 0.2187 | 13.9303 |
| 0.4743 | 1.0 | 1401 | 0.2158 | 13.9593 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.12.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2