Whisper Large v2 PL
This model is a fine-tuned version of bardsai/whisper-large-v2-pl on the Common Voice 11.0 and the FLEURS datasets. It achieves the following results on the evaluation set:
- Loss: 0.3684
- Wer: 7.2802
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0047 | 1.35 | 700 | 0.3428 | 8.5562 |
| 0.0011 | 2.7 | 1400 | 0.3605 | 7.5505 |
| 0.0003 | 4.05 | 2100 | 0.3684 | 7.2802 |
License
This model is released under the Apache License 2.0, like its base model bardsai/whisper-large-v2-pl and openai/whisper-large-v2.
It was fine-tuned during the Hugging Face Whisper Fine-Tuning Event (December 2022) on:
- Common Voice 11.0 (Polish), CC0 1.0, Mozilla Foundation
- FLEURS (Polish), CC BY 4.0, Google
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2