Whisper Tiny Polish
This model is a fine-tuned version of openai/whisper-tiny on the upmedic/common_voice_upmedic default dataset. It achieves the following results on the evaluation set:
- Loss: 0.5465
- Wer: 39.3239
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: 32
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4653 | 0.5 | 1000 | 0.5846 | 42.8452 |
| 0.3402 | 1.44 | 2000 | 0.5465 | 39.3239 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1