whisper-tiny-minds14-en
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: 0.8739
- Wer: 0.320790
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0001 | 125.0 | 500 | 0.8046 | 30.4133 |
| 0.0001 | 250.0 | 1000 | 0.8565 | 31.8322 |
| 0.0001 | 375.0 | 1500 | 0.8739 | 32.0790 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4
Model tree for BinhMinhs10/whisper-tiny-minds14-en
Base model
openai/whisper-tinyDataset used to train BinhMinhs10/whisper-tiny-minds14-en
Evaluation results
- Wer on PolyAI/minds14self-reported0.321