metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-lt-liepa2_30-v5
results: []
whisper-small-lt-liepa2_30-v5
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4076
- Wer: 40.6009
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.624 | 0.0471 | 1000 | 0.6192 | 54.5544 |
| 0.5057 | 0.0942 | 2000 | 0.5086 | 47.4484 |
| 0.4446 | 0.1413 | 3000 | 0.4534 | 44.3991 |
| 0.4181 | 0.1884 | 4000 | 0.4218 | 42.0514 |
| 0.404 | 0.2355 | 5000 | 0.4076 | 40.6009 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0