metadata
library_name: transformers
base_model: 7ocho/WMACv2
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: WMACv2.1
results: []
WMACv2.1
This model is a fine-tuned version of 7ocho/WMACv2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3403
- Wer: 53.6579
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: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4811 | 0.2338 | 1000 | 0.3687 | 54.9924 |
| 0.4310 | 0.4675 | 2000 | 0.3403 | 53.6579 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2