Whisper tiny Greek Punctuation 4k - Chee Li
This model is a fine-tuned version of openai/whisper-base on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.7115
- Wer: 173.9809
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 |
|---|---|---|---|---|
| 0.3988 | 4.5872 | 1000 | 0.6457 | 92.3703 |
| 0.1543 | 9.1743 | 2000 | 0.6497 | 138.2941 |
| 0.0779 | 13.7615 | 3000 | 0.6882 | 164.6308 |
| 0.0498 | 18.3486 | 4000 | 0.7115 | 173.9809 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
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 CheeLi03/whisper-tiny-el-puct-4k
Base model
openai/whisper-base