Whisper Tiny Rus - Chee Li
This model is a fine-tuned version of openai/whisper-tiny on the Google Fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6000
- Wer: 75.2138
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 |
|---|---|---|---|---|
| 0.1479 | 5.4645 | 1000 | 0.4968 | 79.2090 |
| 0.0266 | 10.9290 | 2000 | 0.5468 | 83.7386 |
| 0.0087 | 16.3934 | 3000 | 0.5872 | 75.7215 |
| 0.0066 | 21.8579 | 4000 | 0.6000 | 75.2138 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for CheeLi03/whisper-tiny-rus
Base model
openai/whisper-tiny