Whisper Large V3 HU Full - snoopyben27
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0911
- Wer: 8.8609
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: 8
- 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: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1301 | 0.3299 | 1000 | 0.1351 | 14.5084 |
| 0.1324 | 0.6598 | 2000 | 0.1208 | 13.2777 |
| 0.1136 | 0.9898 | 3000 | 0.1066 | 11.5548 |
| 0.0471 | 1.3197 | 4000 | 0.1030 | 10.3788 |
| 0.0337 | 1.6496 | 5000 | 0.0955 | 9.8045 |
| 0.0311 | 1.9795 | 6000 | 0.0875 | 9.2438 |
| 0.0108 | 2.3095 | 7000 | 0.0911 | 8.8609 |
Framework versions
- Transformers 4.42.2
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1