p6_commonvoice_mild
This model is a fine-tuned version of honzapucalek/p6_commonvoice_16_1 on the honzapucalek/p6_mild cs dataset. It achieves the following results on the evaluation set:
- Loss: 0.6098
- Wer: 0.1592
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 |
---|---|---|---|---|
0.0001 | 46.51 | 1000 | 0.5156 | 0.1606 |
0.0 | 93.02 | 2000 | 0.5644 | 0.1584 |
0.0 | 139.53 | 3000 | 0.5888 | 0.1577 |
0.0 | 186.05 | 4000 | 0.6044 | 0.1592 |
0.0 | 232.56 | 5000 | 0.6098 | 0.1592 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 3
Model tree for honzapucalek/p6_commonvoice_mild
Base model
honzapucalek/p6_commonvoice_16_1Evaluation results
- Wer on honzapucalek/p6_mild cstest set self-reported0.159