whisper-small-french
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: 0.4855
- Wer: 75.74
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2425 | 0.3717 | 500 | 0.5077 | 63.87 |
| 0.2029 | 0.7435 | 1000 | 0.4878 | 67.57 |
| 0.1262 | 1.1152 | 1500 | 0.4881 | 71.65 |
| 0.125 | 1.4870 | 2000 | 0.4855 | 75.74 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.10.0+cu128
- Datasets 2.21.0
- Tokenizers 0.19.1