Whisper Small et - Common Voice+FLEURS
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0, FLEURS dataset. It achieves the following results on the evaluation set:
- Loss: 0.8754
- Wer: 42.4844
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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.0094 | 10.0 | 1000 | 0.7125 | 43.4085 |
| 0.0024 | 20.01 | 2000 | 0.7960 | 42.1795 |
| 0.0012 | 30.01 | 3000 | 0.8237 | 41.8961 |
| 0.0006 | 40.02 | 4000 | 0.8627 | 41.7853 |
| 0.0004 | 51.0 | 5000 | 0.8754 | 42.4844 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 2