whisper-small-en-US
This model is a fine-tuned version of CordwainerSmith/whisper-tiny-PolyAI-minds14 on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Wer Ortho: 0.0012
- Wer: 0.0012
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0 | 1.79 | 50 | 0.0000 | 0.0012 | 0.0012 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 4
Model tree for evertonaleixo/whisper-small-en-US
Base model
openai/whisper-tinyDataset used to train evertonaleixo/whisper-small-en-US
Evaluation results
- Wer on PolyAI/minds14self-reported0.001