Whisper Tiny Ro - Romanian
This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4750
- Wer: 189.8559
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.38 | 1.8 | 1000 | 0.5265 | 149.3835 |
| 0.1647 | 3.6 | 2000 | 0.4707 | 158.4737 |
| 0.093 | 5.4 | 3000 | 0.4725 | 186.1567 |
| 0.064 | 7.19 | 4000 | 0.4750 | 189.8559 |
Framework versions
- Transformers 4.28.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.