<!-- 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-calls-small
This model is a fine-tuned version of openai/whisper-small on the None dataset. Just a test, probably not a very good model
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.076 | 4.03 | 1000 | 0.0481 | 4.1883 |
| 0.0068 | 8.06 | 2000 | 0.0049 | 0.6362 |
| 0.0011 | 12.1 | 3000 | 0.0012 | 0.0157 |
| 0.0005 | 16.13 | 4000 | 0.0006 | 0.0 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1
- Tokenizers 0.13.2
