luigisaetta/whisper-tiny2-it
This model is a fine-tuned version of openai/whisper-tiny on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4686
- Wer: 25.9110
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 |
|---|---|---|---|---|
| 0.5765 | 2.01 | 1000 | 0.5728 | 32.2181 |
| 0.3726 | 4.02 | 2000 | 0.5035 | 28.4606 |
| 0.2789 | 6.04 | 3000 | 0.4861 | 26.7894 |
| 0.2996 | 8.05 | 4000 | 0.4694 | 26.0279 |
| 0.2925 | 10.06 | 5000 | 0.4686 | 25.9110 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2