Whisper da-nst
This model is a fine-tuned version of openai/whisper-medium on the common_voice_14_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7234
- Wer: 35.3094
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0133 | 4.04 | 1000 | 0.6362 | 48.9279 |
| 0.0025 | 9.04 | 2000 | 0.6635 | 37.4731 |
| 0.0001 | 14.03 | 3000 | 0.6959 | 34.1296 |
| 0.0001 | 19.03 | 4000 | 0.7166 | 35.1821 |
| 0.0 | 24.03 | 5000 | 0.7234 | 35.3094 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.1
- Downloads last month
- 6