whisper-large-v2-paper_
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4133
- Wer: 47.7467
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: 2e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 1.0 | 143 | 0.3626 | 71.8596 |
| No log | 2.0 | 286 | 0.3398 | 50.4925 |
| No log | 3.0 | 429 | 0.3426 | 52.2600 |
| 0.3684 | 4.0 | 572 | 0.3541 | 46.2800 |
| 0.3684 | 5.0 | 715 | 0.3721 | 46.6114 |
| 0.3684 | 6.0 | 858 | 0.4133 | 47.7467 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.7.0
- Tokenizers 0.13.2