metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- automatic-speech-recognition,whisper
- generated_from_trainer
metrics:
- wer
model-index:
- name: GAL500
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Enpas/GALKG
type: Enpas/GALKG
metrics:
- name: Wer
type: wer
value: 25.21137586471945
GAL500
This model is a fine-tuned version of openai/whisper-small on the Enpas/GALKG dataset. It achieves the following results on the evaluation set:
- Loss: 0.2507
- Wer: 25.2114
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5194 | 0.3199 | 1000 | 0.4919 | 45.8570 |
| 0.4237 | 0.6398 | 2000 | 0.3681 | 37.4251 |
| 0.349 | 0.9597 | 3000 | 0.3047 | 30.5457 |
| 0.2235 | 1.2796 | 4000 | 0.2758 | 27.5404 |
| 0.188 | 1.5995 | 5000 | 0.2507 | 25.2114 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.1