wav2vec2-base-lang-id
This model is a fine-tuned version of facebook/wav2vec2-base on the common_language dataset. It achieves the following results on the evaluation set:
- Loss: 11.3684
- Accuracy: 0.0284
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: 0.0003
- train_batch_size: 24
- eval_batch_size: 3
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- 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: 0.1
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 45.8136 | 1.0 | 232 | 11.3684 | 0.0284 |
| 45.4635 | 2.0 | 464 | 11.3664 | 0.0284 |
| 34.2305 | 3.0 | 696 | 11.3563 | 0.0284 |
Framework versions
- Transformers 5.0.0.dev0
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.2