<!-- 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-ft-cy
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: 0.3752
- Wer: 22.6542
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: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.4353 | 0.83 | 1000 | 0.4644 | 30.1879 |
0.2679 | 1.66 | 2000 | 0.3911 | 24.5253 |
0.166 | 2.49 | 3000 | 0.3739 | 22.9167 |
0.1179 | 3.32 | 4000 | 0.3752 | 22.6542 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3