Whisper Large Five 5K None - Chee Li
This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.1774
- Wer: 10.1251
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: 600
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0557 | 1.0560 | 1000 | 0.1488 | 11.4913 |
| 0.0171 | 2.1119 | 2000 | 0.1522 | 9.5367 |
| 0.0085 | 3.1679 | 3000 | 0.1630 | 8.6409 |
| 0.0015 | 4.2239 | 4000 | 0.1705 | 10.7759 |
| 0.0007 | 5.2798 | 5000 | 0.1774 | 10.1251 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for CheeLi03/whisper-L-5k
Base model
openai/whisper-large-v3