Whisper Tiny MINDS-14 en-US
This model is a fine-tuned version of openai/whisper-tiny on the MINDS-14 (en-US) dataset. It achieves the following results on the evaluation set:
- Loss: 0.5708
- Wer Ortho: 0.3183
- Wer: 0.3158
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 251
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Wer Ortho |
|---|---|---|---|---|---|
| 0.0066 | 8.7719 | 250 | 0.5708 | 0.3158 | 0.3183 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.8.0+cu126
- Datasets 2.21.0
- Tokenizers 0.20.3
- Downloads last month
- 25
Model tree for Rohith9059/whisper-tiny-minds14-en-us
Base model
openai/whisper-tinyDataset used to train Rohith9059/whisper-tiny-minds14-en-us
Evaluation results
- Wer on MINDS-14 (en-US)self-reported0.316