whisper-tiny-minds14-en-us
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6374
- Wer Ortho: 0.3313
- Wer: 0.3341
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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0011 | 17.8571 | 500 | 0.6374 | 0.3313 | 0.3341 |
| 0.0002 | 35.7143 | 1000 | 0.6906 | 0.3344 | 0.3377 |
| 0.0001 | 53.5714 | 1500 | 0.7214 | 0.3350 | 0.3377 |
| 0.0001 | 71.4286 | 2000 | 0.7428 | 0.3356 | 0.3388 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for markredito/whisper-tiny-minds14-en-us
Base model
openai/whisper-tinyDataset used to train markredito/whisper-tiny-minds14-en-us
Evaluation results
- Wer on PolyAI/minds14self-reported0.334