whisper-small-sorani
This model is a fine-tuned version of openai/whisper-small on the common voice v15 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0334
- Wer: 0.0613
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: 56
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1005 | 0.55 | 1000 | 0.1405 | 0.2743 |
| 0.0711 | 1.09 | 2000 | 0.0858 | 0.1772 |
| 0.0609 | 1.64 | 3000 | 0.0585 | 0.1151 |
| 0.02 | 2.19 | 4000 | 0.0408 | 0.0789 |
| 0.0169 | 2.74 | 5000 | 0.0334 | 0.0613 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0