Whisper small nl - Michel Mesquita
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0321
- Wer: 1.8286
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1097 | 0.4685 | 1000 | 0.1142 | 7.6755 |
| 0.0724 | 0.9370 | 2000 | 0.0621 | 4.0514 |
| 0.0307 | 1.4055 | 3000 | 0.0412 | 2.6727 |
| 0.0285 | 1.8740 | 4000 | 0.0321 | 1.8286 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for kvanberendonck-bethel/whisper-small-nl
Base model
openai/whisper-small