<!-- 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-medium.en
This model is a fine-tuned version of openai/whisper-medium.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4445
- Wer: 10.5080
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: 32
- 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 |
|---|---|---|---|---|
| 0.3016 | 0.12 | 500 | 0.3002 | 10.9478 |
| 0.3978 | 1.1 | 1000 | 0.2896 | 11.2599 |
| 0.1703 | 2.07 | 1500 | 0.3014 | 12.2218 |
| 0.0386 | 3.05 | 2000 | 0.3422 | 10.8046 |
| 0.0094 | 4.02 | 2500 | 0.3770 | 10.3559 |
| 0.017 | 4.14 | 3000 | 0.4025 | 10.7524 |
| 0.0064 | 5.12 | 3500 | 0.4214 | 10.5347 |
| 0.0117 | 6.09 | 4000 | 0.4445 | 10.5080 |
Framework versions
- Transformers 4.29.0
- Pytorch 1.14.0a0+44dac51
- Datasets 2.12.0
- Tokenizers 0.13.3
