Whisper Small Ro - VM
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9886
- Wer: 46.1084
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0603 | 3.69 | 1000 | 0.8196 | 51.4218 |
| 0.0073 | 7.38 | 2000 | 0.9190 | 55.0526 |
| 0.0033 | 11.07 | 3000 | 0.9629 | 45.7936 |
| 0.0011 | 14.76 | 4000 | 0.9886 | 46.1084 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 17
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for VMadalina/whisper-small-ro-music2text
Base model
openai/whisper-small