sereer-omp
This model is a fine-tuned version of patrickvonplaten/wav2vec2-base-timit-demo on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 2.9097
- Cer: 0.9946
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: 0.0001
- train_batch_size: 7
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 4
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.8012 | 4.0 | 4 | 3.4396 | 0.9191 |
| 3.1791 | 8.0 | 8 | 3.1790 | 0.9946 |
| 2.8864 | 12.0 | 12 | 3.1554 | 0.9946 |
| 2.7819 | 16.0 | 16 | 2.9383 | 0.9946 |
| 2.7258 | 20.0 | 20 | 2.9097 | 0.9946 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 9
Model tree for taiyintaiyang/sereer-omp
Base model
patrickvonplaten/wav2vec2-base-timit-demo