wav2vec2-large-xlsr-53-first-try
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0619
- 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: 0.001
- train_batch_size: 8
- eval_batch_size: 16
- 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: 1200
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 13.2136 | 4.0 | 500 | 3.6904 | 1.0 |
| 3.5149 | 8.0 | 1000 | 3.4839 | 1.0 |
| 3.3866 | 12.0 | 1500 | 3.3931 | 1.0 |
| 3.3312 | 16.0 | 2000 | 3.2477 | 1.0 |
| 3.1749 | 20.0 | 2500 | 3.0619 | 1.0 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0