<!-- 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-tiny.en
This model is a fine-tuned version of openai/whisper-tiny.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3883
- Wer: 14.9814
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: 128
- eval_batch_size: 128
- 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 |
|---|---|---|---|---|
| 0.4727 | 2.04 | 500 | 0.4062 | 16.9369 |
| 0.2717 | 5.04 | 1000 | 0.3271 | 15.3713 |
| 0.2022 | 8.04 | 1500 | 0.3251 | 15.2362 |
| 0.1483 | 11.03 | 2000 | 0.3438 | 14.1539 |
| 0.0833 | 14.03 | 2500 | 0.3583 | 15.5601 |
| 0.0848 | 17.03 | 3000 | 0.3755 | 14.8514 |
| 0.0475 | 20.02 | 3500 | 0.3849 | 15.0281 |
| 0.0424 | 23.02 | 4000 | 0.3883 | 14.9814 |
Framework versions
- Transformers 4.29.1
- Pytorch 1.14.0a0+44dac51
- Datasets 2.12.0
- Tokenizers 0.13.3
