Whisper Small Ro - VM3
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: 0.9589
- Wer: 44.1405
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 |
|---|---|---|---|---|
| 0.0533 | 3.69 | 1000 | 0.7937 | 49.6507 |
| 0.0046 | 7.38 | 2000 | 0.9042 | 44.5046 |
| 0.0038 | 11.07 | 3000 | 0.9342 | 46.4331 |
| 0.001 | 14.76 | 4000 | 0.9589 | 44.1405 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.
Model tree for VMadalina/whisper-small-protv-17-ro-music2text2
Base model
openai/whisper-small