Whisper small mn
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7131
- Wer: 50.3222
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: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.314 | 2.38 | 600 | 0.6038 | 58.2896 |
| 0.0776 | 4.76 | 1200 | 0.5787 | 52.4574 |
| 0.0083 | 7.14 | 1800 | 0.6481 | 51.0048 |
| 0.0031 | 9.52 | 2400 | 0.6928 | 50.7099 |
| 0.0014 | 11.9 | 3000 | 0.7131 | 50.3222 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2