whisper-mg
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1375
- Wer: 7.0732
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: 1
- 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: 2500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8228 | 35.7143 | 500 | 0.1301 | 8.2927 |
| 0.0001 | 71.4286 | 1000 | 0.1337 | 7.3171 |
| 0.0 | 107.1429 | 1500 | 0.1352 | 7.0732 |
| 0.0 | 142.8571 | 2000 | 0.1368 | 7.0732 |
| 0.0 | 178.5714 | 2500 | 0.1375 | 7.0732 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1