metadata
library_name: peft
language:
- fr
license: apache-2.0
base_model: openai/whisper-small
tags:
- base_model:adapter:openai/whisper-small
- lora
- transformers
metrics:
- wer
model-index:
- name: Whisper Small Fr - IMT Atlantique X 52 Hertz Full
results: []
Whisper Small Fr - IMT Atlantique X 52 Hertz Full
This model is a fine-tuned version of openai/whisper-small on the FullDatabase dataset. It achieves the following results on the evaluation set:
- Loss: 0.6708
- Wer: 0.3327
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3574 | 0.4762 | 20 | 1.4124 | 0.3671 |
| 1.1555 | 0.9524 | 40 | 1.1674 | 0.3728 |
| 0.7839 | 1.4286 | 60 | 0.7497 | 0.3231 |
| 0.4459 | 1.9048 | 80 | 0.6860 | 0.3614 |
| 0.533 | 2.3810 | 100 | 0.6819 | 0.3461 |
| 0.2029 | 2.8571 | 120 | 0.6708 | 0.3327 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1