openai/whisper-large
This model is a fine-tuned version of openai/whisper-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1412
- Wer: 6.7893
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: 32
- 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: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0475 | 2.03 | 500 | 0.1095 | 62.6591 |
| 0.0201 | 5.01 | 1000 | 0.1225 | 16.9285 |
| 0.0044 | 7.03 | 1500 | 0.1312 | 3.6701 |
| 0.0026 | 10.01 | 2000 | 0.1278 | 7.9506 |
| 0.0001 | 12.04 | 2500 | 0.1323 | 17.9186 |
| 0.0001 | 15.02 | 3000 | 0.1386 | 16.3031 |
| 0.0001 | 17.05 | 3500 | 0.1403 | 6.7074 |
| 0.0 | 20.02 | 4000 | 0.1412 | 6.7893 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2