wav2vec2-base-ne-en-finetuned
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9153
- Wer: 100.0
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5453 | 4.9889 | 1905 | 1.3277 | 100.0 |
| 0.9666 | 9.9757 | 3810 | 0.9827 | 100.0 |
| 0.7854 | 14.9626 | 5715 | 0.9204 | 100.0 |
| 0.6823 | 19.9495 | 7620 | 0.9000 | 100.0 |
| 0.6305 | 24.9364 | 9525 | 0.8861 | 100.0 |
| 0.5986 | 29.9233 | 11430 | 0.8831 | 100.0 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 2.21.0
- Tokenizers 0.22.1