openai/whisper-large-v2
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: 0.2854
- Wer: 289.4487
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 |
|---|---|---|---|---|
| 0.2532 | 0.12 | 500 | 0.2796 | 103.4731 |
| 0.2271 | 0.25 | 1000 | 0.2544 | 24.4680 |
| 0.1485 | 1.1 | 1500 | 0.2458 | 222.2511 |
| 0.1961 | 1.22 | 2000 | 0.2384 | 299.0626 |
| 0.0644 | 2.07 | 2500 | 0.2608 | 389.4986 |
| 0.1381 | 2.2 | 3000 | 0.2518 | 330.6300 |
| 0.0492 | 3.05 | 3500 | 0.2898 | 329.1239 |
| 0.0251 | 3.17 | 4000 | 0.2854 | 289.4487 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2