<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 0.1902
- Wer: 10.0204
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 |
|---|---|---|---|---|
| 0.2223 | 0.12 | 500 | 0.2384 | 11.3393 |
| 0.2291 | 0.25 | 1000 | 0.2043 | 10.2326 |
| 0.1116 | 1.04 | 1500 | 0.1999 | 9.9402 |
| 0.1433 | 1.16 | 2000 | 0.1897 | 10.1128 |
| 0.0687 | 1.29 | 2500 | 0.1876 | 9.9270 |
| 0.067 | 2.07 | 3000 | 0.2089 | 10.6712 |
| 0.0819 | 2.2 | 3500 | 0.1962 | 10.3128 |
| 0.0587 | 2.32 | 4000 | 0.1902 | 10.0204 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
