whisper-tiny-finetuned-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: 0.5304
- Wer Ortho: 0.3745
- Wer: 0.3560
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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 3.549 | 1.43 | 40 | 0.7274 | 0.4263 | 0.3967 |
| 0.3686 | 2.86 | 80 | 0.5389 | 0.3671 | 0.3501 |
| 0.2662 | 4.29 | 120 | 0.5264 | 0.3726 | 0.3577 |
| 0.1372 | 5.71 | 160 | 0.5304 | 0.3745 | 0.3560 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1
- Downloads last month
- 10
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for ChuGyouk/whisper-tiny-minds14-en
Base model
openai/whisper-tiny