Whisper Small nan-tw test
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: 1.0321
- Cer: 60.5960
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: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 1.2462 | 2.8571 | 100 | 1.1866 | 68.6033 |
| 0.1817 | 5.7143 | 200 | 1.0125 | 60.3552 |
| 0.0393 | 8.5714 | 300 | 1.0321 | 60.5960 |
Framework versions
- Transformers 4.47.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Jobaula/whisper-small
Base model
openai/whisper-small