<!-- 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. -->
whisper-small-gd
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1180
- Wer: 14.2298
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: 2
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0723 | 0.09 | 250 | 0.2013 | 22.6924 |
| 0.044 | 0.18 | 500 | 0.1826 | 27.3905 |
| 0.1209 | 0.27 | 750 | 0.1705 | 27.2700 |
| 0.0973 | 0.36 | 1000 | 0.1462 | 15.1182 |
| 0.0941 | 0.45 | 1250 | 0.1322 | 15.6603 |
| 0.076 | 0.54 | 1500 | 0.1258 | 18.3557 |
| 0.0967 | 0.63 | 1750 | 0.1203 | 14.8020 |
| 0.0757 | 0.72 | 2000 | 0.1180 | 14.2298 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
