whisper-tiny-minds14
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: 0.5059
- Wer Ortho: 0.3510
- Wer: 0.3359
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: 150
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 1.8453 | 1.79 | 50 | 0.7554 | 0.4318 | 0.3920 |
| 0.3097 | 3.57 | 100 | 0.4897 | 0.3646 | 0.3489 |
| 0.1089 | 5.36 | 150 | 0.5059 | 0.3510 | 0.3359 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 2
Model tree for fisheggg/whisper-small-dv
Base model
openai/whisper-tinyDataset used to train fisheggg/whisper-small-dv
Evaluation results
- Wer on PolyAI/minds14self-reported0.336