wav2vec2_milDB
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: 2.6994
- Wer: 1.0
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 2.0257 | 10.9890 | 1000 | 1.6873 | 1.0 |
| 1.0671 | 21.9780 | 2000 | 1.6131 | 1.0 |
| 2.4045 | 32.9670 | 3000 | 2.6980 | 1.0 |
| 2.5542 | 43.9560 | 4000 | 2.7001 | 1.0 |
| 2.5504 | 54.9451 | 5000 | 2.6994 | 1.0 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.19.1